© 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. 1820
    Prev
    Next
    INDEX
    Explanations

    python function definitions

    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
    ا
    4.26
    в
    3.18
    en
    2.95
     widz
    2.84
    Caractéristiques
    2.72
     miliar
    2.70
    된
    2.66
    ယာ
    2.66
     apoi
    2.63
    fabricated
    2.63
    POSITIVE LOGITS
    us
    3.19
    د
    3.16
    LevelLinking
    3.14
    ہ
    2.80
    ug
    2.75
    StoredKeys
    2.74
    дят
    2.70
    果た
    2.66
    ु
    2.65
    ス
    2.64
    Activations Density 0.157%

    No Known Activations