© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73940
    Prev
    Next
    INDEX
    Explanations

    list comprehensions with 'in'

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

    This neuron doesn’t respond to any of the shown tokens (i.e. it remains inactive on all of them).

    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
    7
    -1.80
    6
    -1.73
    4
    -1.69
    3
    -1.67
    5
    -1.66
    9
    -1.53
    2
    -1.51
     дополнитель
    -1.48
    更为
    -1.47
    8
    -1.46
    POSITIVE LOGITS
     these
    1.95
     as
    1.74
     this
    1.52
     and
    1.52
     the
    1.46
     a
    1.44
     on
    1.38
    tyimages
    1.38
     ezek
    1.34
     empfehlen
    1.30
    Activations Density 0.004%

    No Known Activations