© 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. 16027
    Prev
    Next
    INDEX
    Explanations

    problems and specifications

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

    The neuron activates on technical parameter or metric terms—words that name measurable settings or specifications (e.g. “liquid product variation,” “printing range,” “location information,” “search limit”).

    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
     iconLine
    -0.95
    뱅
    -0.95
    ixas
    -0.88
    Giu
    -0.85
     armis
    -0.85
     الاط
    -0.84
     ชั้น
    -0.84
     zudem
    -0.81
    无疑
    -0.81
    FARE
    -0.81
    POSITIVE LOGITS
     particular
    0.88
     bad
    0.85
    requirements
    0.84
     requirements
    0.84
     previous
    0.83
     necesitamos
    0.82
     negative
    0.81
     losing
    0.80
     constraints
    0.80
     miss
    0.79
    Activations Density 0.163%

    No Known Activations