© 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. 72352
    Prev
    Next
    INDEX
    Explanations

    classifications or categories

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

    This neuron activates on words naming collectives or named categories (e.g. “voters,” “syndrome,” “cohort,” “sector,” “chamber,” etc.).

    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
     each
    -1.41
    vább
    -1.15
     every
    -1.09
     từng
    -1.07
     different
    -1.06
    orsche
    -1.06
    Each
    -1.05
    çamento
    -1.02
    -1.02
    makeText
    -1.00
    POSITIVE LOGITS
    這些
    1.22
    hese
    1.21
     BrowserModule
    1.18
    这类
    1.16
     этих
    1.09
     these
    1.09
     tarz
    1.09
    这些人
    1.06
    这些
    1.05
    These
    1.04
    Activations Density 0.057%

    No Known Activations