© 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. 10-GEMMASCOPE-RES-131K
    7. 112959
    Prev
    Next
    INDEX
    Explanations

    x-prefixed key-value pairs

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

    the character 'X' followed by a hyphen in technical contexts like headers, API parameters, and variable names.

    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
    a
    -1.59
    mathrm
    -1.54
    .’
    -1.48
    ”
    -1.46
    ↵↵
    -1.44
    (
    -1.43
    「
    -1.40
    B
    -1.27
    I
    -1.26
    >
    -1.23
    POSITIVE LOGITS
    Fourni
    1.48
    岖
    1.40
    mería
    1.38
     zanim
    1.38
    AJAS
    1.36
     แล้ว
    1.33
    讹
    1.31
     penchant
    1.30
    ρεί
    1.28
     escuchadas
    1.28
    Activations Density 0.126%

    No Known Activations