© 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. 105759
    Prev
    Next
    INDEX
    Explanations

    Mormons, practice, negotiation, infants, Deaf

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

    simple linear, Linked List, Prime Conjecture, blood pressure

    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
    ה
    0.63
    вої
    0.49
    חת
    0.48
    હેરા
    0.47
    ,【
    0.46
     シート
    0.46
    llium
    0.46
     protective
    0.45
    গ
    0.44
     sphing
    0.44
    POSITIVE LOGITS
    بت
    0.47
     बेटर
    0.46
     tanpa
    0.45
    bett
    0.44
     nếu
    0.43
     situation
    0.42
     negotiation
    0.41
     salaried
    0.41
    赔
    0.41
     négoci
    0.40
    Activations Density 0.001%

    No Known Activations