© 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. 1823
    Prev
    Next
    INDEX
    Explanations

    pre- hyphenated words

    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
    u
    3.15
    in
    2.88
     sorry
    2.77
    و
    2.73
    ある
    2.69
    м
    2.54
    л
    2.47
     alberga
    2.47
    ן
    2.40
    ers
    2.38
    POSITIVE LOGITS
     Wenn
    2.29
    ा
    2.29
    च
    2.17
     말미암아
    2.01
    े
    1.96
    geordnet
    1.95
    も
    1.93
     следующий
    1.89
    aal
    1.86
    ाइवेट
    1.85
    Activations Density 0.166%

    No Known Activations