© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64230
    Prev
    Next
    INDEX
    Explanations

    groups affected by challenges

    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_34/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
     if
    -1.38
     for
    -1.29
     that
    -1.12
     when
    -1.09
     people
    -1.03
     larger
    -0.99
    _
    -0.98
     unmöglich
    -0.93
     dovuto
    -0.93
     %
    -0.91
    POSITIVE LOGITS
     who
    1.88
    affected
    1.75
     facing
    1.60
     affected
    1.59
     Affected
    1.54
    facing
    1.36
    Affected
    1.27
    Facing
    1.23
     Meille
    1.18
     afectados
    1.15
    Activations Density 0.074%

    No Known Activations