© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99463
    Prev
    Next
    INDEX
    Explanations

    list of items

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

    This neuron detects lengthy runs of whitespace (indentation) before code tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     that
    -1.74
    Those
    -1.61
     would
    -1.55
     However
    -1.51
     Those
    -1.45
    Since
    -1.44
     rusak
    -1.36
     its
    -1.35
     from
    -1.34
    Beskrivelse
    -1.34
    POSITIVE LOGITS
    //
    1.58
    なので
    1.34
    

    1.28
    ,​
    1.22
     [],
    1.22
    ‘
    1.21
    §
    1.20
    cant
    1.20
     [
    1.19
     quintessential
    1.18
    Activations Density 0.016%

    No Known Activations