© 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. 54503
    Prev
    Next
    INDEX
    Explanations

    technical terms and entities

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

    This neuron detects standalone numeric tokens (i.e. numbers or numeric values) 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
    ють
    -1.19
    際の
    -1.13
     This
    -1.12
    >.</
    -1.08
     jopa
    -1.05
     вересня
    -1.05
    område
    -1.04
    也非常
    -1.01
    柠
    -1.00
    MIRA
    -1.00
    POSITIVE LOGITS
    但她
    1.12
     why
    1.10
    糴
    1.04
    があるので
    1.02
     SHOWS
    0.97
    meanor
    0.96
     intestino
    0.95
     து
    0.92
    来到了
    0.91
     rootReducer
    0.91
    Activations Density 0.335%

    No Known Activations