© 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-16K
    7. 2167
    Prev
    Next
    INDEX
    Explanations

    Content policy labels

    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
    er
    3.19
    াতাড়ি
    3.14
    o
    2.77
    даги
    2.77
    hammer
    2.73
    ம்பரிய
    2.73
    बै
    2.73
    фика
    2.71
    calorie
    2.65
    s
    2.65
    POSITIVE LOGITS
     bie
    3.38
     sapply
    3.30
     сами
    3.30
     urges
    3.27
     urge
    3.21
     cnt
    3.19
     multitudes
    3.10
     initialState
    3.04
    uploads
    3.03
     overlap
    2.99
    Activations Density 0.427%

    No Known Activations