© 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. 113120
    Prev
    Next
    INDEX
    Explanations

    .htaccess and .Net configurations

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

    the beginning of technical Q&A posts that start with a period (like ".htaccess" or ".NET").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron spotlights punctuation marks (particularly backslashes and hyphens) used in mathematical/LaTeX notation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    s
    -2.75
     There
    -2.44
     and
    -2.23
    or
    -2.23
    }$
    -2.13
    there
    -2.11
     could
    -2.06
    E
    -1.99
    "
    -1.98
    There
    -1.95
    POSITIVE LOGITS
    虯
    2.55
    ’,
    2.52
    緜
    2.48
    怱
    2.44
    —”
    2.41
    伥
    2.41
    絰
    2.38
    旆
    2.30
     signifikan
    2.27
     menyenangkan
    2.23
    Activations Density 0.001%

    No Known Activations