© 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. 22-GEMMASCOPE-RES-131K
    7. 72590
    Prev
    Next
    INDEX
    Explanations

    until a specific state

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

    This neuron detects imperative cooking or food-preparation action verbs (e.g., combine, stir, cook, microwave, toss).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    lorin
    -1.20
    continues
    -1.16
     esfuer
    -1.16
     Hauptstadt
    -1.15
    ELTS
    -1.15
     prevé
    -1.15
    それを
    -1.12
     presencial
    -1.10
     requiere
    -1.09
    ulite
    -1.09
    POSITIVE LOGITS
     your
    1.17
    不僅
    1.13
     handcuffs
    1.13
    夠
    1.13
     сначала
    1.11
    ях
    1.07
     planer
    1.07
    大部分
    1.06
    🦴
    1.05
    Both
    1.04
    Activations Density 0.005%

    No Known Activations