© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129928
    Prev
    Next
    INDEX
    Explanations

    pick, pickled, pick-up, pick list

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

    The neuron activates on any token containing the substring “pick,” i.e. it’s a detector for “pick.”

    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
    ↵
    -4.19
    <em>
    -3.94
     $\
    -3.80
    (
    -3.64
    *
    -3.56
    >
    -3.34
    =
    -3.31
    на
    -3.27
    ↵↵
    -3.27
    //
    -3.23
    POSITIVE LOGITS
    嚒
    3.58
    鉏
    3.58
    駡
    3.20
    wakili
    3.19
    噲
    3.17
    噐
    3.17
    Ꮞ
    3.14
    
    3.06
    genodigd
    3.05
    modellen
    3.03
    Activations Density 0.014%

    No Known Activations