© 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. 93437
    Prev
    Next
    INDEX
    Explanations

    schedule, quality, license

    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
     ब्ल
    -0.80
    celia
    -0.79
    chst
    -0.79
    袅
    -0.78
    ereien
    -0.77
     قب
    -0.77
    stadion
    -0.77
     feder
    -0.77
    cznie
    -0.76
    stwie
    -0.76
    POSITIVE LOGITS
    Упаковка
    0.81
     osią
    0.81
    ity
    0.80
    µ
    0.75
    <h2>
    0.75
    
    0.74
     abiding
    0.73
     NS
    0.73
     femenino
    0.73
    <h3>
    0.73
    Activations Density 0.008%

    No Known Activations