© 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. 83959
    Prev
    Next
    INDEX
    Explanations

    indie, Wilde, frontal baldness

    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
    }
    -2.89
    ing
    -2.77
    k
    -2.44
     untuk
    -2.44
    T
    -2.34
    ᯅ
    -2.31
    I
    -2.30
    ቍ
    -2.25
     защита
    -2.25
    鹛
    -2.23
    POSITIVE LOGITS
    ون
    2.64
    </em>
    2.63
    </strong>
    2.28
     been
    2.19
    ле
    2.16
    麈
    2.16
    多かった
    2.11
     autonomia
    2.08
     However
    2.00
    Afficher
    2.00
    Activations Density 0.005%

    No Known Activations