© 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. 21070
    Prev
    Next
    INDEX
    Explanations

    0 or control registers

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

    The neuron detects numeric literals (integer, hexadecimal, or floating-point 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_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
    Instead
    -1.70
    colgante
    -1.41
     大全
    -1.38
    Rather
    -1.29
    他の
    -1.27
    horloge
    -1.26
    entuk
    -1.25
    espé
    -1.23
    Through
    -1.23
     других
    -1.23
    POSITIVE LOGITS
     it
    1.45
     there
    1.32
     $
    1.32
    al
    1.30
    $
    1.29
    е
    1.27
    graphies
    1.23
    f
    1.22
    k
    1.21
    ],
    1.16
    Activations Density 0.021%

    No Known Activations