© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66872
    Prev
    Next
    INDEX
    Explanations

    Cardio, Optically, Stalwart

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

    The neuron responds to standalone numeric tokens (sequences of digits) 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_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
     it
    -1.40
     baratas
    -1.29
     colaboradores
    -1.20
    pielen
    -1.16
     its
    -1.13
    ・「
    -1.12
    setTimestamp
    -1.10
    ف
    -1.09
    źródło
    -1.09
    ändern
    -1.07
    POSITIVE LOGITS
    了许多
    1.27
    chi
    1.25
    ……….
    1.20
     flamboyant
    1.19
    0
    1.16
     stalwart
    1.16
    3
    1.16
     wondrous
    1.16
    ons
    1.14
     dată
    1.13
    Activations Density 0.001%

    No Known Activations