© 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. 22-GEMMASCOPE-RES-131K
    7. 73269
    Prev
    Next
    INDEX
    Explanations

    programming dimensions lengths allocation

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

    The neuron fires on tokens that contain digits—that is, it detects numeric literals or identifiers with embedded 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_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
     in
    -2.03
     or
    -1.98
     from
    -1.91
     this
    -1.89
     while
    -1.87
     when
    -1.83
     as
    -1.77
     with
    -1.75
     on
    -1.75
     one
    -1.70
    POSITIVE LOGITS
     luscious
    1.26
     Dinas
    1.22
     tôt
    1.21
     WIL
    1.20
     acuerdos
    1.17
    potentially
    1.16
     terse
    1.13
    currently
    1.13
    similar
    1.12
     "~
    1.12
    Activations Density 0.004%

    No Known Activations