© 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. 94522
    Prev
    Next
    INDEX
    Explanations

    protein sequence character

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

    technical computing and machine learning

    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
     incre
    0.45
     საშ
    0.44
     осно
    0.43
    грани
    0.42
     पुस्त
    0.42
     suspicious
    0.41
     増
    0.41
     ++)
    0.41
    申し込み
    0.40
     incremento
    0.40
    POSITIVE LOGITS
    low
    0.48
    cop
    0.48
    rank
    0.47
    field
    0.46
    count
    0.46
    temp
    0.45
    kill
    0.45
    k
    0.45
    p
    0.45
    z
    0.45
    Activations Density 0.002%

    No Known Activations