© 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. 111536
    Prev
    Next
    INDEX
    Explanations

    android application configuration

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

    line breaks or newlines in code, especially after closing braces, brackets, or semicolons in programming contexts.

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

    This neuron fires on runs of space characters (indentation) rather than on actual 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_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
     to
    -2.34
     then
    -1.73
    :
    -1.53
     ثم
    -1.49
     Then
    -1.49
     their
    -1.42
     Potencia
    -1.41
    亟
    -1.41
     seasoned
    -1.39
     with
    -1.35
    POSITIVE LOGITS
    arities
    1.42
    TOGGLE
    1.35
    好吃的
    1.29
     футболка
    1.24
    AGAIN
    1.23
    等は
    1.23
    щита
    1.22
    ifier
    1.22
    atively
    1.21
    頂きました
    1.20
    Activations Density 0.102%

    No Known Activations