© 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. 34-GEMMASCOPE-RES-131K
    7. 77851
    Prev
    Next
    INDEX
    Explanations

    self-awareness, cognitive, stereotypes

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

    The neuron detects domain-specific academic jargon and methodological keywords (e.g. heuristic, familiarity, context, influence) commonly found in research‐paper titles and abstracts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     nozzles
    -0.84
     schwach
    -0.75
    ниях
    -0.74
     lockers
    -0.73
     Aut
    -0.72
    捜査
    -0.71
     valeurs
    -0.71
    twilight
    -0.70
     آرام
    -0.70
     행
    -0.68
    POSITIVE LOGITS
    criptions
    0.82
    fontWeight
    0.82
    lière
    0.81
    schemas
    0.77
    staticmethod
    0.75
     endorsed
    0.74
     todėl
    0.73
     diagnostic
    0.71
    дай
    0.71
    ोज
    0.70
    Activations Density 0.118%

    No Known Activations