© 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. 84316
    Prev
    Next
    INDEX
    Explanations

    genotypes

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

    words related to genetic analysis, particularly the term "genotype" and related concepts.

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

    The neuron fires on occurrences of the string “toLowerCase” (and similar “LowerCase” method names) in code.

    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
     If
    -2.14
     schwarze
    -2.13
    ⢧
    -2.05
     Virtually
    -2.03
     blaue
    -2.00
    IN
    -2.00
    𨭆
    -1.99
     cérami
    -1.96
     Allowing
    -1.95
    ون
    -1.95
    POSITIVE LOGITS
    龊
    2.69
    啖
    2.69
     unangemess
    2.66
    .
    2.31
    縷
    2.22
     vollständ
    2.17
    ⢫
    2.16
    ")
    2.14
    apatalk
    2.05
    IFUL
    2.05
    Activations Density 0.001%

    No Known Activations