© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48388
    Prev
    Next
    INDEX
    Explanations

    fear or confidence

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

    This neuron primarily activates on words that express an emotional state or subjective attitude (e.g. fear, scared, hesitant, confident).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    )};
    -1.30
    Avant
    -1.23
     pomiędzy
    -1.23
     pagado
    -1.21
     devait
    -1.14
     ferner
    -1.14
    ocidade
    -1.13
     HAVE
    -1.10
     WANT
    -1.09
     legjobb
    -1.08
    POSITIVE LOGITS
     even
    1.30
     anything
    1.13
    confidence
    1.13
    confident
    1.13
     here
    1.12
     such
    1.10
     because
    1.07
     trusting
    1.06
     confi
    1.06
     连
    1.05
    Activations Density 0.058%

    No Known Activations