© 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. 13947
    Prev
    Next
    INDEX
    Explanations

    social groups and conditions

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

    The neuron activates on specialized, domain‐specific technical or topical nouns and phrases commonly found in academic or research writing.

    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
     teras
    -1.50
     envelo
    -1.44
     particules
    -1.43
     oignons
    -1.41
     mariposa
    -1.41
     emot
    -1.37
     linge
    -1.34
     disiplin
    -1.33
     MATHEMAT
    -1.32
     vasco
    -1.32
    POSITIVE LOGITS
     due
    1.46
     currently
    1.44
     выгод
    1.26
     oraz
    1.23
     current
    1.23
     Current
    1.22
     given
    1.18
     actualmente
    1.16
     Besitzer
    1.16
     Due
    1.11
    Activations Density 0.078%

    No Known Activations