© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112659
    Prev
    Next
    INDEX
    Explanations

    code and programming languages

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

    variable declarations and assignments in programming code.

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

    The neuron is detecting numeric literals (integers and decimals) in the document.

    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
     it
    -1.79
     
    -1.40
    ,
    -1.34
     if
    -1.27
     in
    -1.26
     "
    -1.22
     Direktor
    -1.16
    忍者
    -1.15
    -
    -1.14
                            
    -1.11
    POSITIVE LOGITS
    泚
    1.67
     pollici
    1.60
    ;%%
    1.56
     Gennaio
    1.54
     arabe
    1.51
     ghz
    1.51
     leone
    1.48
    ...\
    1.47
     hemel
    1.46
     rosario
    1.45
    Activations Density 0.014%

    No Known Activations