© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123549
    Prev
    Next
    INDEX
    Explanations

    bile salts and ductsSqlParameter declaration

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

    the word "SqlParameter" in programming code or the word "bile" in medical/scientific text.

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

    This neuron spikes on specialized technical or scientific jargon terms (e.g. programming class names like “SqlParameter” or domain‐specific nouns like “bile”).

    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
     cbd
    -2.55
     של
    -2.25
    岀
    -2.20
     und
    -2.11
     militant
    -2.06
     onze
    -2.06
     场
    -2.06
     da
    -2.02
    —
    -2.02
    麴
    -1.98
    POSITIVE LOGITS
    </h1>
    2.91
    0
    2.59
    or
    2.55
    </strong>
    2.50
    this
    2.44
    self
    2.22
    жке
    2.20
     Setelah
    2.17
     剧照
    2.16
    v
    2.14
    Activations Density 0.016%

    No Known Activations