© 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. 8340
    Prev
    Next
    INDEX
    Explanations

    spit out

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

    The neuron activates on occurrences of the verb “spit” (in any form: spit, spits, spitting, spat).

    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
    婞
    -2.30
    N
    -2.22
     sesuai
    -2.16
    轳
    -2.14
     persever
    -2.13
    磲
    -2.11
    変換
    -2.08
    手続き
    -2.08
    $}}
    -2.08
    </sup>
    -2.08
    POSITIVE LOGITS
    '
    4.03
    </h3>
    2.53
     unſ
    2.34
     Перейти
    2.31
     abhängig
    2.11
    ⢌
    2.00
    </h1>
    1.98
    </i>
    1.95
    1.94
    wakili
    1.92
    Activations Density 0.007%
    No Known Activations