© 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. 34-GEMMASCOPE-RES-131K
    7. 57447
    Prev
    Next
    INDEX
    Explanations

    integer limits and maximum values

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

    This neuron detects integer-related tokens—numeric literals, integer types, and constants (e.g. “int”, “Integer.MAX_VALUE”, numeric digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    jetbrains
    -0.79
    teva
    -0.76
    속
    -0.75
     альтерна
    -0.74
    Velocity
    -0.74
     baixa
    -0.73
     olmak
    -0.72
    ȩ
    -0.70
     velocity
    -0.70
    erokee
    -0.70
    POSITIVE LOGITS
     Maximum
    1.16
    Limits
    1.13
     INT
    1.12
    limits
    1.12
    Overflow
    1.05
     overflows
    1.05
     Limits
    1.04
     MAX
    1.03
     overflow
    1.02
     Max
    1.00
    Activations Density 0.042%

    No Known Activations