© 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. 47520
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code snippets

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

    The neuron fires on numeric tokens—particularly multi‐digit numbers.

    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
    SPEC
    -0.79
    ते
    -0.79
    anding
    -0.78
     laba
    -0.76
    ﻴ
    -0.75
     sores
    -0.73
     nini
    -0.73
    UNA
    -0.72
    ebi
    -0.72
     speculate
    -0.71
    POSITIVE LOGITS
     $(
    1.70
     (
    1.27
    $(
    1.18
    ^{*}(
    1.14
    *(
    1.14
    <>(
    1.01
    )*(
    1.00
    }(
    1.00
    (
    0.99
     }(
    0.97
    Activations Density 0.074%

    No Known Activations