© 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. 78813
    Prev
    Next
    INDEX
    Explanations

    support library extended

    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
     system
    -0.82
     ION
    -0.74
    Qualifications
    -0.69
    THESIS
    -0.69
    システム
    -0.66
     Earnings
    -0.66
     Brou
    -0.66
    Sistema
    -0.66
     RAIN
    -0.65
     służ
    -0.65
    POSITIVE LOGITS
    orothy
    0.81
    εκ
    0.80
     Holz
    0.78
    getInputStream
    0.74
     perdeu
    0.69
     переда
    0.68
    няка
    0.68
    convention
    0.67
    拈
    0.67
    corp
    0.65
    Activations Density 0.065%

    No Known Activations