© 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. 73492
    Prev
    Next
    INDEX
    Explanations

    copyrighted material or goalie

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

    This neuron fires on tokens beginning with the “go” sound (the letter sequence go, or its equivalents in other scripts), i.e. it detects words starting with that “go”‐prefix.

    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
    t
    -3.02
    by
    -2.86
    m
    -2.83
    what
    -2.73
    <bos>
    -2.63
    when
    -2.52
     поэтому
    -2.48
    狆
    -2.44
    It
    -2.42
    you
    -2.34
    POSITIVE LOGITS
    ’
    3.08
    俅
    2.86
    ↵
    2.72
    嫑
    2.63
    洐
    2.61
    泔
    2.59
    を利用
    2.52
    燹
    2.48
    を始め
    2.44
    倥
    2.44
    Activations Density 0.001%

    No Known Activations