© 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. 224177
    Prev
    Next
    INDEX
    Explanations

    emergency situations

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

    tiny, wedding, onion

    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
     maggior
    0.57
     I
    0.56
     Liber
    0.55
     γιατί
    0.50
     Ville
    0.50
     .”
    0.50
     estren
    0.49
     composée
    0.48
     protože
    0.48
     Pon
    0.47
    POSITIVE LOGITS
    Suppl
    0.57
     defied
    0.48
    льної
    0.47
    हेलो
    0.46
     defy
    0.46
    annotate
    0.46
    _{\
    0.46
    洗
    0.46
    يله
    0.45
    isalpha
    0.45
    Activations Density 0.001%

    No Known Activations