© 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. 10-GEMMASCOPE-RES-131K
    7. 66168
    Prev
    Next
    INDEX
    Explanations

    option=true/false

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

    This neuron detects numeric literals (digits or decimals) in the text.

    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
     from
    -1.17
     Vortrag
    -1.15
     Then
    -1.14
     Frühl
    -1.13
     kemudian
    -1.11
     our
    -1.10
    種類の
    -1.10
    naeus
    -1.09
     zwanzig
    -1.07
     of
    -1.06
    POSITIVE LOGITS
     cerveza
    1.22
     Secretaria
    1.17
     custos
    1.16
     vinos
    1.13
    縈
    1.12
    हि
    1.09
    ریح
    1.09
     perro
    1.09
     guitarra
    1.09
    神奈川
    1.09
    Activations Density 0.065%

    No Known Activations