© 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. 2832
    Prev
    Next
    INDEX
    Explanations

    code initialization comments

    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
    دان
    -0.93
    این
    -0.85
    пыта
    -0.84
    SequentialGroup
    -0.83
    geç
    -0.82
    タ
    -0.82
    setCellValue
    -0.81
    神经
    -0.79
    رون
    -0.78
    Bal
    -0.76
    POSITIVE LOGITS
    newly
    0.88
    resources
    0.84
     asisti
    0.80
    obtain
    0.79
     apalagi
    0.78
    leads
    0.77
    weren
    0.77
    重置
    0.77
    wasn
    0.76
     resources
    0.76
    Activations Density 0.000%

    No Known Activations