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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 171
    Prev
    Next
    INDEX
    Explanations

    lexicon

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ncia
    0.55
    র
    0.55
    rifice
    0.49
     LaSalle
    0.49
     Fit
    0.48
     Run
    0.48
    ن
    0.46
    nue
    0.46
     Stop
    0.46
    rini
    0.45
    POSITIVE LOGITS
    页面存档备份
    0.63
    associated
    0.62
    typically
    0.61
     implying
    0.59
     ausreiche
    0.59
    munderover
    0.58
    𝘷
    0.57
    promoting
    0.57
     līdz
    0.57
     sayıda
    0.56
    Activations Density 0.676%

    No Known Activations