© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 78076
    Prev
    Next
    INDEX
    Explanations

    first-team, first-grade, first-class

    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
     frio
    -0.80
    ioneta
    -0.77
    ãy
    -0.73
    뇨
    -0.69
    endamento
    -0.66
    stdafx
    -0.65
     Aguirre
    -0.65
    шая
    -0.63
    ห์
    -0.63
    ಿನ
    -0.63
    POSITIVE LOGITS
     First
    4.44
    First
    4.25
     first
    3.69
    first
    3.48
     FIRST
    3.27
    FIRST
    3.20
    getFirst
    2.88
     getFirst
    2.80
     первого
    2.72
    第一
    2.70
    Activations Density 0.062%

    No Known Activations