© 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. 37448
    Prev
    Next
    INDEX
    Explanations

    foreign languages and expressions

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

    final part of processes

    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
    RATE
    0.50
    Launcher
    0.48
    iggs
    0.48
    H
    0.46
    ля
    0.46
    PEN
    0.46
    launcher
    0.46
    Champion
    0.46
    healthcare
    0.46
    ಡ
    0.45
    POSITIVE LOGITS
     اشاره
    0.55
     Zwei
    0.54
     dessus
    0.52
     කල
    0.51
     Rücken
    0.50
     traduire
    0.49
    ný
    0.49
     Deux
    0.48
     الذي
    0.47
     সীম
    0.46
    Activations Density 0.000%

    No Known Activations