© 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. 59342
    Prev
    Next
    INDEX
    Explanations

    21-hydroxylase

    np_acts-logits-general · gemini-2.5-flash-lite

    Bible verse or reference numbers, especially chapter and verse citations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     ziehen
    -0.89
    只有
    -0.82
    warnai
    -0.77
     焼き
    -0.77
     недо
    -0.76
    aaral
    -0.76
    ividu
    -0.76
    sopp
    -0.76
    此前
    -0.75
    传统的
    -0.75
    POSITIVE LOGITS
    はある
    0.81
    ティスト
    0.75
     rowIndex
    0.72
     amin
    0.72
     Harsh
    0.71
     Jealous
    0.71
     Regularly
    0.71
    }$.\\
    0.71
    crimination
    0.71
     INI
    0.71
    Activations Density 0.040%

    No Known Activations