© 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. 92677
    Prev
    Next
    INDEX
    Explanations

    Dai-

    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
     ocurre
    -0.69
    iole
    -0.68
    ícula
    -0.68
    ophylla
    -0.68
     диагности
    -0.67
     Union
    -0.67
     flexibilidad
    -0.67
     Verhältnis
    -0.66
     accuracy
    -0.66
     artem
    -0.66
    POSITIVE LOGITS
     代
    1.05
    代
    0.99
    خصة
    0.79
    代价
    0.77
     Courtney
    0.75
     Meredith
    0.75
    璃
    0.74
     表
    0.73
    saga
    0.73
    赭
    0.73
    Activations Density 0.015%

    No Known Activations