© 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. 10-GEMMASCOPE-RES-131K
    7. 14677
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ferien
    -1.10
    ofus
    -1.00
    Serbia
    -1.00
    =’
    -0.97
    getDisplay
    -0.96
     matang
    -0.94
    Emotion
    -0.92
    bluza
    -0.92
     eier
    -0.92
    spective
    -0.91
    POSITIVE LOGITS
     you
    1.37
    Using
    1.00
     pronoun
    0.96
    Very
    0.93
    ぉ
    0.92
     This
    0.92
    Eight
    0.90
     Gesetze
    0.90
    Once
    0.89
     they
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.