© 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. 97156
    Prev
    Next
    INDEX
    Explanations

    joining the, with God, visa stamp, significant effort

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

    binary classification

    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
     αποτε
    0.46
    Boston
    0.44
    ammer
    0.44
    Bets
    0.42
    <0x9D>
    0.41
    rds
    0.40
    arcz
    0.39
     tava
    0.39
    baka
    0.39
    BELL
    0.39
    POSITIVE LOGITS
    ጅም
    0.46
    collectibles
    0.45
    ambio
    0.44
     распро
    0.43
     நன்றாக
    0.43
    䡆
    0.43
    스러운
    0.43
     своим
    0.41
     Treasures
    0.41
     deformation
    0.41
    Activations Density 0.002%

    No Known Activations