© 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. 75928
    Prev
    Next
    INDEX
    Explanations

    anyone asking for help

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

    The neuron fires primarily on the word “Anyone” (often at the start of a question).

    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
    antado
    -0.97
    şa
    -0.97
    ไม่
    -0.97
    λέον
    -0.96
    ——–
    -0.93
    ต้อง
    -0.93
    
    -0.93
    🤝
    -0.92
     and
    -0.91
    =’
    -0.90
    POSITIVE LOGITS
     know
    1.60
     have
    1.41
     has
    1.30
     knows
    1.25
     can
    1.23
     experienced
    1.23
     happen
    1.19
     here
    1.19
     any
    1.14
     experience
    1.08
    Activations Density 0.037%

    No Known Activations