© 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. 102593
    Prev
    Next
    INDEX
    Explanations

    hit the

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

    The neuron consistently flags occurrences of the verb “hit” (including its form “hitting”) in various phrases.

    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
    u
    -2.08
    。
    -1.82
    ↵↵
    -1.80
    e
    -1.78
    2
    -1.77
    ...
    -1.71
    其他
    -1.59
    *
    -1.48
    \
    -1.47
    <
    -1.46
    POSITIVE LOGITS
     It
    2.03
    咴
    1.98
    porsche
    1.81
    ଃ
    1.77
    szt
    1.74
    鲣
    1.71
    沕
    1.71
    ICIENCY
    1.70
    颏
    1.70
    汭
    1.69
    Activations Density 0.009%

    No Known Activations