© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71531
    Prev
    Next
    INDEX
    Explanations

    symbols preceding code tokens

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

    The neuron selectively fires on numeric literals or tokens containing digits (e.g. version numbers, numeric constants, line counts).

    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
     also
    -1.23
     from
    -1.11
     could
    -1.04
     if
    -1.03
     Also
    -1.00
     If
    -0.97
     was
    -0.95
     we
    -0.95
     Usually
    -0.93
     Apalagi
    -0.93
    POSITIVE LOGITS
     this
    0.96
    趿
    0.94
    ご覧
    0.93
    雖然
    0.93
    ceptive
    0.91
     общественного
    0.90
    ceptable
    0.88
     passos
    0.88
     obvio
    0.88
    cataly
    0.87
    Activations Density 0.012%

    No Known Activations