© 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. 2688
    Prev
    Next
    INDEX
    Explanations

    1 and -1

    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
     in
    -0.94
     eight
    -0.93
     with
    -0.93
     those
    -0.93
     freckles
    -0.90
     дверей
    -0.89
    štu
    -0.86
     even
    -0.83
    義務
    -0.82
     fifty
    -0.82
    POSITIVE LOGITS
     one
    0.94
    1
    0.89
     אחד
    0.87
     violen
    0.86
    １
    0.85
     hierdie
    0.84
     intrig
    0.84
     applau
    0.83
     laterale
    0.83
     Fiscalía
    0.82
    Activations Density 0.008%

    No Known Activations