© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68459
    Prev
    Next
    INDEX
    Explanations

    english language attribute value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    -3.20
    as
    -2.98
    us
    -2.83
    g
    -2.75
    C
    -2.72
    v
    -2.56
    ti
    -2.55
     the
    -2.52
    er
    -2.50
    F
    -2.50
    POSITIVE LOGITS
    ܞ
    3.02
    鶿
    2.77
    崀
    2.52
    豨
    2.34
    Ꮉ
    2.30
    蟜
    2.27
    𖣔
    2.27
    ৣ
    2.20
     -"
    2.19
    木坂
    2.19
    Activations Density 0.028%

    No Known Activations