© 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. 32325
    Prev
    Next
    INDEX
    Explanations

    created by name

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

    This neuron responds to long runs of whitespace (indentation) in code.

    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
     bakar
    -1.24
     krim
    -1.19
     babak
    -1.18
     rajut
    -1.18
     romantis
    -1.17
     Paket
    -1.16
    libatkan
    -1.16
    瘆
    -1.14
     tatu
    -1.14
     laku
    -1.13
    POSITIVE LOGITS
     on
    2.33
     Mac
    1.44
     Kevin
    1.16
     Andrew
    1.14
     to
    1.13
     as
    1.12
     Michael
    1.11
     MAC
    1.09
    hi
    1.09
     Apple
    1.09
    Activations Density 0.010%

    No Known Activations