© 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. 127724
    Prev
    Next
    INDEX
    Explanations

    MAX_BYTES

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

    The neuron is primarily detecting numeric literals (especially array‐index numbers) in the 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
    ↵
    -1.65
    its
    -1.59
    ise
    -1.52
     itself
    -1.52
    And
    -1.52
     przód
    -1.51
    Its
    -1.46
    などなど
    -1.42
    For
    -1.41
    〜〜
    -1.41
    POSITIVE LOGITS
    ーズン
    1.60
     multitudes
    1.49
    unhofer
    1.47
    viembre
    1.47
    ৄ
    1.45
     Romains
    1.44
     nadie
    1.43
    zette
    1.42
    ůměr
    1.41
    於
    1.38
    Activations Density 0.018%

    No Known Activations