© 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. 134633
    Prev
    Next
    INDEX
    Explanations

    setup an appointment

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

    website, directly, giant

    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
    ずつ
    0.54
     ペット
    0.53
    詳細
    0.50
    ਤਰ
    0.49
     segera
    0.47
     Хоро
    0.47
     설명을
    0.47
    პ
    0.47
     ハン
    0.46
     Dessa
    0.46
    POSITIVE LOGITS
    eing
    0.47
    ekk
    0.46
    呐
    0.44
    elands
    0.44
    觐
    0.43
    mitted
    0.43
    缅
    0.43
    ehl
    0.42
    Parsed
    0.42
    无奈
    0.42
    Activations Density 0.001%

    No Known Activations