© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8960
    Prev
    Next
    INDEX
    Explanations

    someone asking for help

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

    The neuron detects occurrences of the word “someone,” as in pleas for help (“I hope someone can help…”).

    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
     ۱۱
    -1.45
     avto
    -1.43
    ،
    -1.42
    ferien
    -1.34
    蕺
    -1.33
     katal
    -1.32
     risiko
    -1.32
     etui
    -1.28
     modele
    -1.27
     maig
    -1.27
    POSITIVE LOGITS
     from
    1.80
     with
    1.72
     up
    1.54
     them
    1.47
    がありますが
    1.35
     has
    1.33
    がありました
    1.32
     does
    1.31
     is
    1.30
     out
    1.30
    Activations Density 0.076%

    No Known Activations