© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73501
    Prev
    Next
    INDEX
    Explanations

    #include directives and paths

    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
    oric
    -0.70
     col
    -0.69
    เฟ
    -0.69
     consultato
    -0.67
    ントン
    -0.66
    Referencoj
    -0.65
    $("#
    -0.65
     filho
    -0.64
    CVE
    -0.63
    pist
    -0.63
    POSITIVE LOGITS
     invoke
    0.73
     integrate
    0.70
    紝
    0.68
     schwar
    0.67
    titulo
    0.67
    très
    0.66
     dual
    0.66
     basal
    0.66
    Able
    0.66
    احة
    0.64
    Activations Density 0.087%

    No Known Activations