© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22514
    Prev
    Next
    INDEX
    Explanations

    objective-c programming constructs

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

    This neuron fires on numeric literal tokens (i.e. standalone numbers 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_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
     .
    -2.47
    _{
    -2.44
     or
    -2.31
    一月
    -2.14
     and
    -2.14
    )
    -2.11
     [
    -2.11
     f
    -2.09
    信念
    -2.09
    }
    -2.08
    POSITIVE LOGITS
    2
    2.45
    ing
    2.38
    3
    2.25
    5
    2.19
    的同时
    2.17
    羕
    2.14
     スタンド
    2.14
    "> 
    2.13
    8
    2.13
    硨
    2.11
    Activations Density 0.001%

    No Known Activations