© 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. 11304
    Prev
    Next
    INDEX
    Explanations

    coding, dates, ingredients

    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
    то
    2.06
    ته
    1.97
    <i>
    1.95
    bė
    1.85
    ur
    1.80
     व्यस्त
    1.80
    راط
    1.72
    𝘢
    1.68
    ทรัพย์
    1.68
     دفع
    1.65
    POSITIVE LOGITS
    InvariantCulture
    2.29
     eaters
    2.25
    INGER
    2.25
    hanahu
    2.23
     elaboration
    2.21
     kerül
    2.17
     caster
    2.16
    కోండి
    2.16
    cein
    2.13
    creen
    2.13
    Activations Density 0.000%

    No Known Activations