© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9235
    Prev
    Next
    INDEX
    Explanations

    allelic variation and ratios

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

    The neuron detects the letter sequence "lic" especially when it appears in scientific or technical contexts like "allelic" in genetics.

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

    The neuron selectively activates on occurrences of the substring “allel” (as in “allelic,” “allelic variation,” etc.), i.e. mentions of alleles or allelic variation.

    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
    on
    -2.86
     obti
    -2.52
    es
    -2.31
    薷
    -2.27
    на
    -2.27
     “
    -2.20
     ولكن
    -2.19
    和他
    -2.11
    很是
    -2.08
    er
    -2.06
    POSITIVE LOGITS
    lic
    3.17
    ?"
    3.00
    ."
    2.97
    ";
    2.77
    晅
    2.70
    '));
    2.66
    沺
    2.56
    ally
    2.53
    ؟
    2.50
    .";
    2.38
    Activations Density 0.009%

    No Known Activations