© 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. 2410
    Prev
    Next
    INDEX
    Explanations

    systemic conditions or politics

    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
     willow
    -0.83
     basement
    -0.81
     enkelte
    -0.74
    Willow
    -0.74
    conoc
    -0.72
     Willow
    -0.71
    bbero
    -0.71
    NW
    -0.70
     voci
    -0.68
     bı
    -0.68
    POSITIVE LOGITS
     Ray
    1.17
    Ray
    1.04
    oderma
    1.02
    RAY
    0.91
     tightening
    0.88
    érables
    0.85
     RAY
    0.78
     skin
    0.77
     Rays
    0.77
     fingertips
    0.77
    Activations Density 0.071%

    No Known Activations