© 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. 38605
    Prev
    Next
    INDEX
    Explanations

    email subjects and chat identifiers

    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
    The
    -2.05
     and
    -1.84
    </h3>
    -1.83
    новых
    -1.78
    If
    -1.77
    There
    -1.76
     Also
    -1.74
    This
    -1.70
    ApJ
    -1.67
    Following
    -1.66
    POSITIVE LOGITS
     its
    1.88
    danke
    1.81
    meine
    1.77
    潆
    1.70
     possono
    1.68
     them
    1.67
     encuentras
    1.67
    </sup>
    1.67
    lijk
    1.66
     sientes
    1.66
    Activations Density 0.001%

    No Known Activations