© 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. 10846
    Prev
    Next
    INDEX
    Explanations

    code comments or copyright notices

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

    newline characters or line breaks, particularly in source code files with copyright headers and comments.

    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
    ”،
    -1.86
    釭
    -1.60
     colorear
    -1.57
     ?",
    -1.53
    𖡼
    -1.52
     janela
    -1.52
     ilha
    -1.51
     zis
    -1.50
     usuarios
    -1.49
    が必要です
    -1.45
    POSITIVE LOGITS
    </strong>
    2.38
    全都
    1.95
    </sub>
    1.71
    vantaged
    1.70
     esclu
    1.66
    usually
    1.66
    訁
    1.59
    </i>
    1.59
    showthread
    1.58
     conducta
    1.57
    Activations Density 0.034%

    No Known Activations