© 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. 76804
    Prev
    Next
    INDEX
    Explanations

    open standards and formats

    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
    ;\;
    -0.80
     thường
    -0.78
    Traditional
    -0.77
    gleiche
    -0.77
     かけ
    -0.76
     blitt
    -0.75
    netbeans
    -0.75
    ˺
    -0.73
    艺术
    -0.73
    celine
    -0.73
    POSITIVE LOGITS
     standards
    3.81
    standards
    2.94
     Standards
    2.92
    Standards
    2.83
     стандар
    2.61
     STANDARDS
    2.59
     standardization
    2.42
     standard
    2.22
     estándares
    2.06
     standardize
    1.99
    Activations Density 0.224%

    No Known Activations