© 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. 78675
    Prev
    Next
    INDEX
    Explanations

    background art or information

    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
     дости
    -0.76
    зму
    -0.75
     under
    -0.70
     Under
    -0.69
     đứng
    -0.68
    Under
    -0.68
    erst
    -0.65
    academia
    -0.63
     cua
    -0.62
    看法
    -0.62
    POSITIVE LOGITS
    摆手
    0.76
     raisonnable
    0.75
    uchin
    0.73
    经纪
    0.73
    Trent
    0.71
     usize
    0.70
     belakang
    0.69
     shelters
    0.68
    ші
    0.68
    δρο
    0.68
    Activations Density 0.060%

    No Known Activations