© 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. 10977
    Prev
    Next
    INDEX
    Explanations

    for too long

    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
    ard
    1.91
    ขัน
    1.79
    InitTypeDef
    1.73
     floss
    1.71
     LOGIN
    1.70
    ூர்
    1.70
    በት
    1.69
    );
    1.66
    胱
    1.65
    bel
    1.64
    POSITIVE LOGITS
     noqa
    2.31
    वेदना
    2.27
    songwriter
    2.26
    ﺳ
    2.25
     Poets
    2.24
     mutter
    2.23
     алфа
    2.22
    اته
    2.17
     المرس
    2.16
     onlook
    2.13
    Activations Density 0.013%

    No Known Activations