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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 981
    Prev
    Next
    INDEX
    Explanations

    regret even

    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
    e
    5.54
    ي
    5.20
    ০
    5.16
    er
    4.84
    ి
    4.82
    ে
    4.65
    ه
    4.64
    ein
    4.64
    ה
    4.61
    a
    4.48
    POSITIVE LOGITS
    ting
    3.05
    𝐭
    2.89
    𝐤
    2.73
    াস
    2.71
    𝐠
    2.64
    𝐬
    2.63
    𝙍
    2.62
    𝐫
    2.62
    ными
    2.55
    ませ
    2.49
    Activations Density 3.993%

    No Known Activations