© 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. 193943
    Prev
    Next
    INDEX
    Explanations

    topics and articles

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

    data analysis and timeframes

    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
     பாம்பு
    0.51
     Букмекердик
    0.48
    toHaveBeenCalled
    0.46
    牘
    0.46
     தாவர
    0.45
    arrayOf
    0.45
    ály
    0.44
     manly
    0.43
    mUserManager
    0.43
    状
    0.43
    POSITIVE LOGITS
     Fernanda
    0.50
     Cie
    0.49
     Ave
    0.49
     Lifetime
    0.47
    But
    0.47
     Psik
    0.47
     Camilla
    0.46
     KIM
    0.46
     But
    0.45
     Gim
    0.45
    Activations Density 0.000%

    No Known Activations