© 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. 22-GEMMASCOPE-RES-131K
    7. 33238
    Prev
    Next
    INDEX
    Explanations

    integer type declarations

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

    The neuron is detecting standalone numeric literals (decimal integer constants) 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_22/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
     stratég
    -1.40
     politika
    -1.38
    衚
    -1.31
    undaki
    -1.30
     osoba
    -1.28
     surpren
    -1.27
    PENDAHULUAN
    -1.27
    引言
    -1.26
    ᥀
    -1.25
     fotografii
    -1.24
    POSITIVE LOGITS
     is
    1.43
     it
    1.40
    It
    1.25
    ńcz
    1.22
     there
    1.20
    撓
    1.16
     chon
    1.16
    3
    1.15
    type
    1.14
    &
    1.14
    Activations Density 0.009%

    No Known Activations