© 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. 33495
    Prev
    Next
    INDEX
    Explanations

    identifying explanatory factors and predictors

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

    The neuron fires on statistical‐methods language—terms referring to variables, factors, characteristics, predictors, and association analyses.

    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
    Tant
    -1.20
    staben
    -1.12
     diras
    -1.07
    ✴
    -1.05
    ján
    -1.03
     saia
    -1.02
    ituation
    -1.02
    französ
    -1.02
     النبات
    -1.02
    月刊
    -1.00
    POSITIVE LOGITS
     factors
    1.79
     variables
    1.48
    因素
    1.10
     ücret
    1.09
     задний
    1.08
     listed
    1.05
     factor
    1.04
     عوامل
    1.03
     encontré
    1.01
     モダン
    1.01
    Activations Density 0.174%

    No Known Activations