© 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. 77386
    Prev
    Next
    INDEX
    Explanations

    Union station

    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
    ис
    -0.90
    gamesh
    -0.87
    顯
    -0.76
     Question
    -0.73
     Dans
    -0.72
     тек
    -0.71
    rshire
    -0.70
     tentunya
    -0.69
     主要
    -0.69
     komplex
    -0.68
    POSITIVE LOGITS
    </i>
    1.11
    </em>
    0.97
    </u>
    0.88
    дитесь
    0.85
     який
    0.84
    ელი
    0.84
    🗂
    0.84
    蜆
    0.83
     більш
    0.82
     различни
    0.79
    Activations Density 0.000%

    No Known Activations