© 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. 219039
    Prev
    Next
    INDEX
    Explanations

    signalling status

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

    AI writing

    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
    ເລັກ
    0.57
    ètre
    0.50
     auxqu
    0.50
    otá
    0.50
     arv
    0.48
     கூறிய
    0.48
     说
    0.47
     impeding
    0.47
     津
    0.47
     acción
    0.46
    POSITIVE LOGITS
    o
    0.54
    torch
    0.51
    dict
    0.50
    tex
    0.49
    dataset
    0.49
    the
    0.49
    -
    0.48
    Dataset
    0.47
    নি
    0.47
    6
    0.47
    Activations Density 0.000%

    No Known Activations