© 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. 238057
    Prev
    Next
    INDEX
    Explanations

    found data

    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
     ግ
    0.56
    EventEmitter
    0.52
    AppLink
    0.50
     февраля
    0.48
    Malformed
    0.47
    áln
    0.47
    емым
    0.47
    }\|_{
    0.46
    TextBlock
    0.46
    avers
    0.46
    POSITIVE LOGITS
     sangue
    0.51
     gaya
    0.50
     rid
    0.49
     tagging
    0.48
     carving
    0.48
     tata
    0.47
     UNIX
    0.47
     name
    0.47
     tên
    0.47
     tingkat
    0.46
    Activations Density 0.001%

    No Known Activations