© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8087
    Prev
    Next
    INDEX
    Explanations

    pow(

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     주는
    0.41
    冋
    0.40
     thawing
    0.39
    Xaml
    0.39
     větš
    0.37
    溺
    0.37
    ahah
    0.36
     ndani
    0.35
    ிறார்கள்
    0.35
    ༢
    0.35
    POSITIVE LOGITS
     సాహిత
    0.31
    瑋
    0.31
    wort
    0.31
    বিষয়
    0.31
     জাতীয়
    0.30
     especial
    0.30
     in
    0.30
     helpers
    0.30
    requis
    0.30
     Doct
    0.30
    Activations Density 0.000%

    No Known Activations