© 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. 112270
    Prev
    Next
    INDEX
    Explanations

    tech news and tech domains

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

    the word "tech" in URLs, domain names, and technical contexts.

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

    The neuron is triggered by the token “tech,” i.e. it detects occurrences of the exact string “tech” (as in URLs or words).

    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
    i
    -3.44
    er
    -3.14
     ''
    -2.63
    e
    -2.63
     The
    -2.59
    ه
    -2.59
    </b>
    -2.58
    ed
    -2.56
    a
    -2.55
    p
    -2.39
    POSITIVE LOGITS
    秾
    3.25
     复古
    3.17
    ╽
    3.16
    秶
    3.14
     TÉCNICA
    3.03
    CHREIB
    3.02
    蹋
    3.02
     简约
    3.02
    鼇
    3.00
    følgelig
    2.86
    Activations Density 0.004%

    No Known Activations