© 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. 34-GEMMASCOPE-RES-131K
    7. 73579
    Prev
    Next
    INDEX
    Explanations

    negative emotional states

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

    This neuron detects roots of words expressing strong emotional reactions or intense psychological states (e.g., trauma, shock, frustration, exhaustion).

    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
     όλα
    -0.75
     tratt
    -0.75
     becomes
    -0.73
     became
    -0.73
    となりました
    -0.72
    Oferta
    -0.72
     ALFRED
    -0.71
    contrar
    -0.71
     odio
    -0.71
    rogate
    -0.71
    POSITIVE LOGITS
    ized
    1.63
    ened
    1.42
    ed
    1.41
    ned
    1.32
    zed
    1.30
    ified
    1.24
    ured
    1.23
    ised
    1.20
    tered
    1.19
    ated
    1.10
    Activations Density 0.044%

    No Known Activations