© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 247147
    Prev
    Next
    INDEX
    Explanations

    listings and sales information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proclaims
    0.54
     poni
    0.50
     aşağı
    0.48
     sobald
    0.48
     authorizes
    0.46
     प्रमाण
    0.45
    聲
    0.45
     streng
    0.45
     ক্ষেত্রে
    0.45
     synchronize
    0.45
    POSITIVE LOGITS
    epsilon
    0.51
    日本の
    0.45
    ebra
    0.45
    ordinal
    0.44
    儚
    0.43
    SSS
    0.43
    finals
    0.42
    TPP
    0.42
     Brighton
    0.42
     препарат
    0.42
    Activations Density 0.000%

    No Known Activations