© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2519
    Prev
    Next
    INDEX
    Explanations

    `<script>` tags and code blocks

    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
    ,
    1.85
     and
    1.81
    .
    1.62
     AND
    1.58
    ;
    1.53
     и
    1.46
     و
    1.44
    ,,
    1.32
     (
    1.31
     -
    1.30
    POSITIVE LOGITS
    िमी
    1.84
    र्गत
    1.84
     piş
    1.78
     criaturas
    1.74
     afiliados
    1.70
     vanligt
    1.70
    ेशनों
    1.68
     impianti
    1.68
    ल्दी
    1.65
    ílio
    1.63
    Activations Density 0.153%

    No Known Activations