© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 196
    Prev
    Next
    INDEX
    Explanations

    numbers, dollar amounts, and counts

    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_16k_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
     وأ
    0.69
     ເ
    0.67
     का
    0.63
     juga
    0.62
     และ
    0.59
    tattoo
    0.59
     همچنین
    0.59
     तथा
    0.57
     Änderung
    0.57
     कसा
    0.57
    POSITIVE LOGITS
     thirties
    0.66
     twenties
    0.64
     seventies
    0.63
    6
    0.62
    ifiably
    0.62
     fives
    0.60
    8
    0.59
     fifties
    0.59
     nDims
    0.59
    5
    0.59
    Activations Density 0.975%

    No Known Activations