© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15532
    Prev
    Next
    INDEX
    Explanations

    trichogramma, trichophyton, trichomonas, neville, marjorie

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

    scientific names of microorganisms, particularly those in the Tricho- genus.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The main thing this neuron does is detect occurrences of the character sequence “trich” (as in scientific names or terms).

    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
    樒
    -2.81
    4
    -2.61
     they
    -2.47
    次
    -2.47
    他的
    -2.45
    ?”
    -2.41
    8
    -2.39
    I
    -2.39
    尤其
    -2.38
    姌
    -2.36
    POSITIVE LOGITS
    𞤢
    3.06
    ༀ
    2.56
    ቍ
    2.41
    鉝
    2.36
    𖡼
    2.25
    诶
    2.23
    甡
    2.22
    hlander
    2.20
    sonaro
    2.17
    錐
    2.17
    Activations Density 0.007%

    No Known Activations