© 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. 87209
    Prev
    Next
    INDEX
    Explanations

    look out for

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

    The neuron detects instances of “look out for” (and close variants like “on the lookout for” or “watch for”) expressing an alert to watch for something.

    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
     When
    -1.59
    殆
    -1.59
     vivos
    -1.56
    derdag
    -1.45
    ULATIONS
    -1.43
     Despite
    -1.42
    但她
    -1.40
     радость
    -1.39
     เมื่อ
    -1.37
    国庆
    -1.37
    POSITIVE LOGITS
    他的
    2.06
    𞤢
    1.84
    ָם
    1.70
    }}=\
    1.69
     связанные
    1.67
     néhány
    1.66
    columnNumber
    1.57
     detalj
    1.57
    jení
    1.55
     inkluder
    1.55
    Activations Density 0.010%

    No Known Activations