© 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. 22-GEMMASCOPE-RES-131K
    7. 130306
    Prev
    Next
    INDEX
    Explanations

    The neuron detects key research variables and constructs (like mediators, predictors, outcomes, and measurement terms) in scientific‐study text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    social-demographic factors and issues

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     vestiti
    -1.27
     النبات
    -1.21
     quelli
    -1.20
    מונות
    -1.18
     vicini
    -1.16
    για
    -1.12
    coledì
    -1.10
    διο
    -1.10
     cucchiai
    -1.10
    Studi
    -1.09
    POSITIVE LOGITS
     (
    1.47
     as
    1.37
    を
    1.15
     factor
    1.11
     in
    1.11
     on
    1.02
    particle
    1.01
     was
    0.98
     alone
    0.97
    :
    0.96
    Activations Density 0.046%

    No Known Activations