© 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. 102849
    Prev
    Next
    INDEX
    Explanations

    CWE vulnerabilities

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

    code comments and technical documentation headers, especially in programming contexts.

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

    The neuron detects decimal numeric tokens (floating‐point values, e.g. “12.25,” “33.75”) in the text.

    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
     becomes
    -1.48
     all
    -1.45
     or
    -1.42
     being
    -1.37
     getting
    -1.31
     so
    -1.27
     in
    -1.26
     Usually
    -1.24
     does
    -1.24
     as
    -1.23
    POSITIVE LOGITS
     francus
    1.63
    лтемелер
    1.48
     höhere
    1.48
    脔
    1.46
     fieles
    1.45
    habitants
    1.45
     toallas
    1.44
    ۲
    1.43
     stara
    1.43
     hogares
    1.43
    Activations Density 0.103%

    No Known Activations