© 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. 168026
    Prev
    Next
    INDEX
    Explanations

    numbers and specific place names

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

    holds your

    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
     архів
    0.51
    к
    0.51
    interpolate
    0.49
    Sw
    0.49
    gel
    0.49
    ASA
    0.48
    Automatically
    0.48
    gallery
    0.48
    ל
    0.47
    LP
    0.46
    POSITIVE LOGITS
    验收
    0.43
     Clemson
    0.42
     economies
    0.41
     Hammers
    0.41
     Stamford
    0.40
    度和
    0.40
    資源
    0.40
     be
    0.40
    經驗
    0.39
     disadvantaged
    0.39
    Activations Density 0.000%

    No Known Activations