© 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. 118808
    Prev
    Next
    INDEX
    Explanations

    someone else's

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

    This neuron fires on occurrences of the word “else” (e.g. “no one else,” “somebody else,” “anyone else”).

    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
     reklama
    -1.95
     efekt
    -1.90
    絝
    -1.88
     ekolog
    -1.84
     唯美
    -1.79
     帅气
    -1.79
    ݮ
    -1.78
    ܆
    -1.76
     serão
    -1.74
     infek
    -1.73
    POSITIVE LOGITS
    p
    2.08
    F
    2.02
    no
    1.97
    h
    1.95
    k
    1.88
    r
    1.86
    2
    1.84
    {\
    1.84
    or
    1.81
    al
    1.80
    Activations Density 0.010%

    No Known Activations