© 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. 113537
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation

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

    commas that separate elements in arrays or function arguments in 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
     your
    -1.65
    ⦑
    -1.35
     will
    -1.33
     or
    -1.31
     annet
    -1.29
    your
    -1.26
    VYMaps
    -1.26
     adonan
    -1.23
     berken
    -1.23
    لد
    -1.23
    POSITIVE LOGITS
    </h3>
    1.52
     некото
    1.38
    _
    1.36
    </i>
    1.33
    création
    1.30
    <th>
    1.28
     possi
    1.27
     Hauteur
    1.27
    </h1>
    1.26
    </blockquote>
    1.26
    Activations Density 0.047%

    No Known Activations