© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7928
    Prev
    Next
    INDEX
    Explanations

    festivals, shows, and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    these
    -2.30
    “
    -1.77
    the
    -1.73
    “-
    -1.73
     следу
    -1.72
    at
    -1.70
    
    -1.70
    geſ
    -1.68
    “:
    -1.66
    “)
    -1.63
    POSITIVE LOGITS
     fallu
    1.91
     fumée
    1.63
    龊
    1.60
     роско
    1.56
    Simplified
    1.56
    洢
    1.53
    ꨄ
    1.52
     作り方
    1.52
     словно
    1.51
    しば
    1.48
    Activations Density 0.047%

    No Known Activations