© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11319
    Prev
    Next
    INDEX
    Explanations

    array map method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ي
    1.50
    خدام
    1.28
    ная
    1.24
    ре
    1.23
    ной
    1.19
    돔
    1.16
    ями
    1.15
    ро
    1.14
    orbit
    1.12
    них
    1.12
    POSITIVE LOGITS
     asseg
    1.38
     Enlarg
    1.31
    <?,
    1.26
     Improve
    1.24
    fonte
    1.22
    što
    1.21
     Improving
    1.19
     Antigen
    1.19
    导致
    1.17
     morto
    1.15
    Activations Density 0.001%

    No Known Activations