© 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. 160398
    Prev
    Next
    INDEX
    Explanations

    trekking, Challenge, Knife, Angel, CIO

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

    specific details

    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
     Copenhagen
    0.43
     Logistics
    0.43
     [
    0.41
     Learning
    0.39
     Sydney
    0.39
     également
    0.38
     unterschiedlich
    0.38
     Financial
    0.37
     Wendy
    0.37
     Campus
    0.36
    POSITIVE LOGITS
     pronotum
    0.49
    larghezza
    0.46
    Strafpunkte
    0.46
    Caracter
    0.43
    ཊ
    0.43
    acelet
    0.43
    ཝ
    0.42
    新款
    0.41
    Pokud
    0.41
    璈
    0.41
    Activations Density 0.000%

    No Known Activations