© 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. 49292
    Prev
    Next
    INDEX
    Explanations

    log4j configuration

    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
     forwarded
    -0.84
    앓
    -0.79
     useCallback
    -0.79
    getSource
    -0.78
    kawasaki
    -0.77
     brachy
    -0.76
     Suf
    -0.76
     exuberant
    -0.73
     regrets
    -0.72
     Syr
    -0.71
    POSITIVE LOGITS
    タリー
    0.81
     Porch
    0.79
    zungs
    0.79
    FATAL
    0.78
    venant
    0.77
     App
    0.75
    crypt
    0.74
    ≃
    0.74
     FAT
    0.74
     Qiu
    0.74
    Activations Density 0.033%

    No Known Activations