© 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. 177625
    Prev
    Next
    INDEX
    Explanations

    direct service, greater than

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

    reaching lower temperatures

    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
    ной
    0.61
    เสียหาย
    0.58
    沧
    0.58
     перемен
    0.56
    ం
    0.55
    轿
    0.55
    ார்
    0.55
    错了
    0.55
    ड़ी
    0.54
    满满
    0.54
    POSITIVE LOGITS
    0.53
     theoret
    0.51
     acutely
    0.50
     patients
    0.50
     i
    0.49
     reduce
    0.48
     intravenously
    0.48
     extremal
    0.48
     experimentally
    0.47
     using
    0.47
    Activations Density 0.005%

    No Known Activations