© 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. 22-GEMMASCOPE-RES-131K
    7. 64632
    Prev
    Next
    INDEX
    Explanations

    absence of undesirable qualities

    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_22/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
     bazı
    -1.16
    Herald
    -1.09
    дото
    -1.05
    を見つけ
    -1.04
    ographie
    -1.04
    堪能
    -1.03
     получают
    -1.02
     biraz
    -1.00
     somewhat
    -1.00
    arschijnlijk
    -1.00
    POSITIVE LOGITS
     any
    1.86
     nor
    1.73
     or
    1.58
     you
    1.46
    有任何
    1.37
     your
    1.35
     unlike
    1.27
     will
    1.25
     ANY
    1.17
     even
    1.16
    Activations Density 0.043%

    No Known Activations