© 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. 57795
    Prev
    Next
    INDEX
    Explanations

    XHTML DTDs and templating delimiters

    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
    ایج
    -0.75
     Mounts
    -0.73
     Copeland
    -0.73
     ATI
    -0.71
     كم
    -0.69
     meningkatkan
    -0.69
    apia
    -0.69
    风
    -0.69
    Cys
    -0.68
    Cumulative
    -0.68
    POSITIVE LOGITS
    ப்ப
    0.77
    ณฑ
    0.69
     establish
    0.68
    splitlines
    0.68
     τ
    0.67
     Gegen
    0.64
     comments
    0.64
     sư
    0.63
     stability
    0.63
     happiness
    0.63
    Activations Density 0.068%

    No Known Activations