© 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. 240290
    Prev
    Next
    INDEX
    Explanations

    custom, design, year

    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
     advised
    0.54
     incompat
    0.53
     encounter
    0.52
    ک
    0.50
     which
    0.50
     downloader
    0.49
     other
    0.49
     adipis
    0.49
     जिनको
    0.48
    ਦ
    0.48
    POSITIVE LOGITS
    isième
    0.51
    is
    0.49
    érapie
    0.46
    крытие
    0.46
    лье
    0.45
    ině
    0.45
    льт
    0.44
    -}\
    0.44
    يون
    0.43
    ίνη
    0.42
    Activations Density 0.000%

    No Known Activations