© 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. 233004
    Prev
    Next
    INDEX
    Explanations

    analysis system, international network

    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
    ח
    0.54
     insanely
    0.50
     imperialism
    0.50
    Deployed
    0.50
     دقی
    0.50
     whereof
    0.49
     ingrained
    0.47
     exiled
    0.47
    deployed
    0.47
    પ
    0.47
    POSITIVE LOGITS
     gemeinsam
    0.48
     एसपी
    0.46
     หมาย
    0.44
     situasi
    0.44
     dol
    0.44
     Pointe
    0.43
     план
    0.43
     binder
    0.42
     Соответ
    0.42
     scarf
    0.42
    Activations Density 0.001%

    No Known Activations