© 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. 102209
    Prev
    Next
    INDEX
    Explanations

    social anthropologist

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

    service and information

    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
    𒅗
    0.54
    StarGo
    0.52
     ऑपरेशन
    0.50
     sogenannten
    0.50
     MOBILE
    0.49
    스의
    0.49
    chargez
    0.48
    <unused45>
    0.48
    ométrique
    0.48
    ك
    0.48
    POSITIVE LOGITS
     is
    0.61
     or
    0.58
     e
    0.55
     experimento
    0.52
     I
    0.52
     work
    0.52
     int
    0.52
     intern
    0.51
    ist
    0.50
     pro
    0.49
    Activations Density 0.000%

    No Known Activations