© 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. 10-GEMMASCOPE-RES-131K
    4. 69168
    Prev
    Next
    INDEX
    Explanations

    ambush and attack

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

    The neuron fires on words describing sudden violent attacks or ambushes.

    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
    2
    -2.38
    o
    -2.03
    4
    -1.89
    0
    -1.72
    V
    -1.66
    over
    -1.58
    3
    -1.58
    6
    -1.55
    as
    -1.55
    5
    -1.55
    POSITIVE LOGITS
    笮
    1.57
    鷓
    1.55
    งิน
    1.49
     byste
    1.47
     AssemblyCulture
    1.45
    GeoNames
    1.45
     aufgrund
    1.45
    ysing
    1.44
    Ᏺ
    1.43
    瞜
    1.41
    Activations Density 0.030%

    No Known Activations