© 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. 10977
    Prev
    Next
    INDEX
    Explanations

    foreign and specific 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_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
    ة
    1.42
    AN
    1.38
    데
    1.38
    т
    1.36
     maturities
    1.34
     Exceptions
    1.28
    тени
    1.28
    चणी
    1.26
    ಾ
    1.26
    이
    1.25
    POSITIVE LOGITS
     ideal
    1.26
    Ideal
    1.20
    ilver
    1.15
     trovare
    1.11
    itivo
    1.10
    ณ์
    1.10
     Anteil
    1.09
    Lk
    1.07
     zap
    1.05
     há
    1.05
    Activations Density 0.000%

    No Known Activations