© 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. 218976
    Prev
    Next
    INDEX
    Explanations

    final output or specifying choices

    np_acts-logits-general · gemini-2.5-flash-lite

    lists of items

    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
     गट
    0.46
    ManagerProxy
    0.44
    atherm
    0.44
     менедж
    0.43
     Invitational
    0.43
    6
    0.43
    group
    0.43
     ৭
    0.43
    IDField
    0.43
     ম্যান
    0.42
    POSITIVE LOGITS
    يع
    0.47
    ونکہ
    0.45
    ều
    0.45
    சால
    0.45
    如何
    0.44
    ಿಂದ
    0.44
    さて
    0.44
     dilated
    0.44
     vrijed
    0.44
    ဘ
    0.44
    Activations Density 0.000%

    No Known Activations