© 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. 10-GEMMASCOPE-RES-131K
    7. 101489
    Prev
    Next
    INDEX
    Explanations

    identifiers and C++ keywords

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

    single capital letters, particularly in technical or formal contexts like code, legal documents, and scientific notation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     was
    -3.05
    一旁
    -2.89
    텃
    -2.81
    ৄ
    -2.70
    </h2>
    -2.69
    饧
    -2.61
    änemark
    -2.55
    ⮜
    -2.53
    埽
    -2.50
    寕
    -2.48
    POSITIVE LOGITS
    I
    3.98
    ↵
    3.56
    If
    3.48
    </u>
    3.48
    4
    2.94
    You
    2.86
    時も
    2.73
    0
    2.73
    C
    2.72
    3
    2.72
    Activations Density 0.216%

    No Known Activations