© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32340
    Prev
    Next
    INDEX
    Explanations

    pencil, sharpener, questions, proverbs, grinding

    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
     pens
    -0.95
     Inks
    -0.93
    インク
    -0.88
    Plasma
    -0.85
     pen
    -0.84
     ink
    -0.84
     inks
    -0.82
     Tsub
    -0.82
    Ink
    -0.78
    डी
    -0.77
    POSITIVE LOGITS
     lead
    1.25
     HB
    1.01
     Lead
    1.01
    lead
    0.92
     leads
    0.89
     sharpen
    0.88
    Lead
    0.86
     eraser
    0.83
     breakage
    0.83
    HB
    0.83
    Activations Density 0.009%

    No Known Activations