© 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. 238749
    Prev
    Next
    INDEX
    Explanations

    recommendations and options

    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
     स्किल
    0.50
     तर
    0.49
    Plain
    0.49
    ୃ
    0.48
    Ｉ
    0.48
    PGS
    0.48
    Mohammed
    0.47
    वरिश
    0.46
    Guesses
    0.46
     ट्रैवल
    0.46
    POSITIVE LOGITS
     আস্তে
    0.49
     ACK
    0.47
     repeatability
    0.47
     fermé
    0.46
     exemplaire
    0.46
    ović
    0.46
     impeccable
    0.46
     SLAs
    0.45
     Configuration
    0.45
    耦
    0.44
    Activations Density 0.001%

    No Known Activations