© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11788
    Prev
    Next
    INDEX
    Explanations

    translation instruction

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens characteristic of formal or technical writing—especially hyphenated compounds, numerals/dates, and acronym-style abbreviations with punctuation.

    oai_token-act-pair · gpt-5Triggered by @smilgaveronika

    tokens that are salient named entities or specific factual tokens (dates, numbers, IDs, and other content-bearing words).

    oai_token-act-pair · gpt-5-miniTriggered by @smilgaveronika
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spectrophot
    1.84
     Pupp
    1.82
    र
    1.79
     Spears
    1.76
     Phen
    1.76
     phen
    1.76
    獨
    1.71
     Currently
    1.70
     và
    1.69
     bhar
    1.67
    POSITIVE LOGITS
     medlem
    1.85
     ذہن
    1.79
     स्लाइड्स
    1.72
     জোগ
    1.71
     możli
    1.68
    baliknya
    1.68
    aturamento
    1.67
    がき
    1.67
     bimestre
    1.65
    쑥
    1.62
    Activations Density 0.000%

    No Known Activations