© 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. 76923
    Prev
    Next
    INDEX
    Explanations

    code, tests, and dates

    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
    meden
    -0.81
    mbrie
    -0.80
     precisamos
    -0.78
    然的
    -0.77
     охра
    -0.76
    
    -0.76
     beard
    -0.75
    ⁸
    -0.74
    fritt
    -0.74
     ο
    -0.74
    POSITIVE LOGITS
     self
    0.82
    skel
    0.80
     during
    0.77
     prevent
    0.77
    stretchr
    0.75
     treball
    0.75
     preventing
    0.74
     continue
    0.73
     Wilkins
    0.73
    됩니다
    0.72
    Activations Density 0.008%

    No Known Activations