© 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. 131806
    Prev
    Next
    INDEX
    Explanations

    enable to carry out

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

    absolute terms

    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
    𝓙
    0.48
    春节
    0.46
    лять
    0.46
    chairman
    0.45
    Diego
    0.45
    ޅ
    0.45
     შემთხვევ
    0.44
    ཧ
    0.44
     सटी
    0.44
    いや
    0.43
    POSITIVE LOGITS
     Walks
    0.48
    ونها
    0.47
     Goes
    0.44
    eraj
    0.44
     Chemists
    0.44
    러
    0.44
     Walking
    0.43
     Provides
    0.43
     Drainage
    0.43
     Leaves
    0.42
    Activations Density 0.000%

    No Known Activations