© 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. 34-GEMMASCOPE-RES-131K
    7. 118102
    Prev
    Next
    INDEX
    Explanations

    hotspot or hot spots

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

    The neuron consistently activates on occurrences of “hot spot(s)” (including hyphenated and concatenated forms).

    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
    HEIM
    -0.72
    چه
    -0.72
    אור
    -0.70
     Tham
    -0.69
    prehensive
    -0.68
     बज
    -0.68
     観
    -0.67
    Caixa
    -0.66
     titulada
    -0.66
     Litecoin
    -0.65
    POSITIVE LOGITS
     hotspots
    5.00
     hotspot
    4.91
     hot
    4.53
    hot
    4.22
     Hot
    3.92
    Hot
    3.86
     Hotspot
    3.73
     HOT
    3.00
    热点
    2.98
    HOT
    2.95
    Activations Density 0.103%

    No Known Activations