© 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. 64929
    Prev
    Next
    INDEX
    Explanations

    protocol, prototype, proto

    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
    logr
    -0.73
     mężczyzn
    -0.72
     Gass
    -0.69
    getLogger
    -0.68
     نی
    -0.68
    듯
    -0.67
    benz
    -0.66
     nhiệm
    -0.65
    меется
    -0.65
    cemic
    -0.65
    POSITIVE LOGITS
     expert
    0.91
     cuidados
    0.84
     라
    0.84
    TRY
    0.83
     proto
    0.81
     Proto
    0.79
    heur
    0.79
     Titanium
    0.77
    expert
    0.77
    PROTO
    0.77
    Activations Density 0.001%

    No Known Activations