© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198600
    Prev
    Next
    INDEX
    Explanations

    quantities and durations

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

    proverbial wisdom

    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
     IN
    0.47
    i
    0.47
    Latitude
    0.46
    Hurricane
    0.45
    FLOW
    0.44
     charg
    0.43
     CHAR
    0.43
    oed
    0.42
     for
    0.41
    ,</
    0.41
    POSITIVE LOGITS
    ኘት
    0.48
    理性
    0.48
     সূত্রে
    0.47
    enciones
    0.46
     সত্যি
    0.46
     তোমাকে
    0.44
    stahl
    0.43
     getest
    0.43
    郆
    0.43
    cando
    0.43
    Activations Density 0.000%

    No Known Activations