© 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. 97440
    Prev
    Next
    INDEX
    Explanations

    local company name and description

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

    sequence and causality

    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
     darkMode
    0.54
     是否
    0.49
    ör
    0.47
    uko
    0.45
     Eltern
    0.44
    ète
    0.43
    apy
    0.43
     条
    0.43
     पंकज
    0.43
     MCP
    0.43
    POSITIVE LOGITS
    অর্চনা
    0.46
    あり
    0.46
     lexic
    0.45
    나무
    0.44
    いろんな
    0.43
    能力
    0.42
    ならない
    0.42
     hypothesize
    0.42
    呵
    0.42
    ർട്ട
    0.41
    Activations Density 0.001%

    No Known Activations