© 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. 59367
    Prev
    Next
    INDEX
    Explanations

    URL paths and code snippets

    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
     Aesthetic
    -0.68
     aesthetic
    -0.67
     sovereignty
    -0.66
    ịp
    -0.65
     Req
    -0.65
    ėse
    -0.65
     Retrieve
    -0.65
    autoconfigure
    -0.64
     wisatawan
    -0.63
     Füße
    -0.63
    POSITIVE LOGITS
    ǝ
    0.73
    ipedia
    0.72
    pur
    0.68
    uncias
    0.67
    ikir
    0.66
    Sampled
    0.65
    Altri
    0.65
     Hydra
    0.65
    нуть
    0.64
     Tori
    0.64
    Activations Density 0.057%

    No Known Activations