© 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. 115172
    Prev
    Next
    INDEX
    Explanations

    follow where he leads

    np_acts-logits-general · gemini-2.5-flash-lite

    prioritize getting

    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
     ஒன்றாக
    0.45
     Command
    0.44
     Epsom
    0.44
     ，
    0.44
     Anaheim
    0.43
     pagamento
    0.42
    endenti
    0.42
     Commanding
    0.42
     منه
    0.42
    ስቃሴ
    0.42
    POSITIVE LOGITS
    вайте
    0.48
     ucz
    0.46
    层次
    0.46
    䄳
    0.45
     विका
    0.44
    ో
    0.44
     разу
    0.44
     بیاکتنې
    0.44
    ährend
    0.44
     schrift
    0.44
    Activations Density 0.000%

    No Known Activations