© 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. 10-GEMMASCOPE-RES-131K
    7. 73325
    Prev
    Next
    INDEX
    Explanations

    causal relationships

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

    The neuron fires on words that express addressing or soothing others’ concerns and providing emotional reassurance (e.g. “assuage,” “concern,” “appreciative,” “supported,” “heard”).

    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
     ésta
    -1.77
     éstas
    -1.70
     éste
    -1.50
     añadió
    -1.47
     menyesuaikan
    -1.46
     it
    -1.45
     entrenar
    -1.42
    ilosop
    -1.41
     éstos
    -1.41
    ürnberg
    -1.38
    POSITIVE LOGITS
    er
    1.82
    0
    1.70
     –
    1.70
    In
    1.66
     how
    1.65
    ’
    1.63
     (
    1.59
    я
    1.55
    v
    1.54
    (
    1.54
    Activations Density 0.018%

    No Known Activations