© 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. 118821
    Prev
    Next
    INDEX
    Explanations

    for ( construct

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

    the keyword "for" at the beginning of loop statements in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     retraso
    -2.20
    唖
    -2.09
    战胜
    -2.03
     templado
    -1.98
     trastorno
    -1.93
     pomi
    -1.90
     による
    -1.88
     kontroli
    -1.84
     desglose
    -1.84
    kurtka
    -1.84
    POSITIVE LOGITS
    !
    2.34
    ....
    2.22
    e
    2.19
    ?
    2.05
    ...
    1.97
    2
    1.95
    不管是
    1.91
    of
    1.89
    '
    1.88
    1
    1.84
    Activations Density 0.011%

    No Known Activations