© 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. 236284
    Prev
    Next
    INDEX
    Explanations

    taking the

    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
     disparity
    0.53
     autopsy
    0.52
     coinc
    0.51
     uncommon
    0.50
     a
    0.46
     requirement
    0.46
    ها
    0.45
     settlements
    0.45
     unintentional
    0.45
    ب
    0.44
    POSITIVE LOGITS
     ስለዚህ
    0.53
    inah
    0.51
     рубе
    0.48
     छात्र
    0.48
     টিক্কা
    0.48
     छात्राओं
    0.47
     ሰዎች
    0.47
     certains
    0.46
    ccccn
    0.46
     NumericVector
    0.46
    Activations Density 0.005%

    No Known Activations