© 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. 11002
    Prev
    Next
    INDEX
    Explanations

    subtle qualities and changes

    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
    ină
    3.13
    ে
    2.83
     комі
    2.75
    arino
    2.74
    𝒖
    2.73
    𝙖
    2.70
    uć
    2.70
    вы
    2.69
    ため
    2.64
     влас
    2.58
    POSITIVE LOGITS
    ೂರ್ಯ
    2.31
    ('$(
    2.23
    عي
    2.21
    <bos>
    2.09
    زين
    2.08
    우스
    2.06
    징
    2.02
    زار
    2.00
    비스
    1.99
    tten
    1.93
    Activations Density 0.004%

    No Known Activations