© 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. 112103
    Prev
    Next
    INDEX
    Explanations

    Go/Unix syscalls

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

    tabs or whitespace used for indentation in structured data or code.

    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
    </h3>
    -2.50
     =
    -2.44
     ALWAYS
    -2.38
    g
    -2.30
    item
    -2.28
    in
    -2.27
     Using
    -2.27
     Getting
    -2.20
    d
    -2.20
     Creating
    -2.14
    POSITIVE LOGITS
    夲
    2.64
    髎
    2.61
    despite
    2.58
     oraș
    2.56
    iffance
    2.53
    '
    2.52
    傒
    2.52
    亹
    2.52
     邸
    2.39
     asisten
    2.36
    Activations Density 0.012%

    No Known Activations