© 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. 10-GEMMASCOPE-RES-131K
    7. 103843
    Prev
    Next
    INDEX
    Explanations

    code snippets from various languages

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

    indentation or whitespace at the beginning of lines in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is triggered by long runs of whitespace (e.g. indentation or multi‐space 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_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
    0
    -2.08
    1
    -1.91
     of
    -1.73
    9
    -1.72
     from
    -1.67
    4
    -1.63
    3
    -1.59
    These
    -1.59
    5
    -1.59
    8
    -1.58
    POSITIVE LOGITS
    ଢ
    2.27
     všech
    1.80
    ᛬
    1.74
    赑
    1.71
    塍
    1.71
    
    1.71
    ſu
    1.67
    ocardial
    1.66
    嵓
    1.66
    ":"+
    1.66
    Activations Density 0.011%

    No Known Activations