© 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. 225841
    Prev
    Next
    INDEX
    Explanations

    bus or skeleton

    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
    Document
    0.55
    Evento
    0.53
    講演
    0.50
    არ
    0.50
    बन
    0.50
    EVENT
    0.50
    の
    0.50
    ス
    0.49
    Network
    0.48
    ส
    0.48
    POSITIVE LOGITS
     temperament
    0.50
     scoff
    0.49
    bindingFields
    0.47
     maize
    0.47
     fave
    0.47
     curled
    0.46
     vices
    0.46
     favourites
    0.46
     mystical
    0.46
     horrifying
    0.46
    Activations Density 0.000%

    No Known Activations