© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33351
    Prev
    Next
    INDEX
    Explanations

    code and mathematics

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

    The neuron strongly activates on numeric literals (digits/numbers) in code snippets.

    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
     tapis
    -1.18
     Komun
    -1.17
    descriptions
    -1.10
    Mű
    -1.09
     their
    -1.09
    Перевод
    -1.09
     jugos
    -1.07
     capítulo
    -1.07
     ralla
    -1.06
     elefante
    -1.04
    POSITIVE LOGITS
    en
    1.13
    C
    1.06
     almeno
    1.05
     probabilidad
    1.05
    or
    1.05
    ↵↵↵↵↵↵↵↵↵↵↵
    1.03
    e
    1.02
     aprire
    1.00
     последу
    0.99
    ↵↵↵↵↵↵
    0.97
    Activations Density 0.000%

    No Known Activations