© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50426
    Prev
    Next
    INDEX
    Explanations

    names of people and mother roles said

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

    The neuron fires on words that mark personal participants or speakers in a narrative (e.g. first‐person pronouns and character nouns).

    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
    HasColumnName
    -1.04
    issez
    -0.90
    Visited
    -0.89
    不仅
    -0.86
     Visits
    -0.86
    不但
    -0.85
    ഐ
    -0.84
     expédié
    -0.84
    곽
    -0.84
     pyram
    -0.83
    POSITIVE LOGITS
     especially
    1.31
     suggested
    1.26
     insist
    1.25
    率先
    1.20
     suggestion
    1.18
     particularly
    1.16
     instig
    1.16
    dib
    1.11
     besonders
    1.09
     insisted
    1.07
    Activations Density 0.035%

    No Known Activations