© 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. 127476
    Prev
    Next
    INDEX
    Explanations

    scanner

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

    The neuron fires on occurrences of the word “scanner” (and closely related “scanning”) in the text.

    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
     ซึ่ง
    -2.75
     was
    -2.73
    她
    -2.69
     olika
    -2.63
    или
    -2.47
    鲠
    -2.44
    ay
    -2.44
     greateſt
    -2.31
     Which
    -2.30
     Your
    -2.28
    POSITIVE LOGITS
     were
    3.36
    紧接着
    2.84
    ;
    2.58
    觔
    2.53
    蠱
    2.36
    剽
    2.25
     postponed
    2.23
    ).
    2.23
     oscura
    2.20
    也得
    2.20
    Activations Density 0.007%

    No Known Activations