© 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. 34-GEMMASCOPE-RES-131K
    7. 62696
    Prev
    Next
    INDEX
    Explanations

    Q: Eat ' Direction

    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
    dera
    -0.75
    ocal
    -0.69
    Voi
    -0.68
     каса
    -0.68
     opposing
    -0.67
    Deadpool
    -0.66
    hield
    -0.66
    ógio
    -0.66
    ować
    -0.65
     Mindanao
    -0.65
    POSITIVE LOGITS
     isolate
    0.93
    FLAG
    0.91
    hende
    0.82
     FLAG
    0.82
     \%)$
    0.82
    traum
    0.80
     Dart
    0.79
    natives
    0.78
    ấm
    0.77
    reten
    0.76
    Activations Density 0.078%

    No Known Activations