© 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. 71919
    Prev
    Next
    INDEX
    Explanations

    musical instruments and performers

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

    The neuron activates on numeric tokens (multi‐digit numbers) 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
    P
    -1.37
     it
    -1.35
     $
    -1.27
    O
    -1.27
     типу
    -1.24
    X
    -1.23
    C
    -1.22
    H
    -1.21
    E
    -1.20
    G
    -1.20
    POSITIVE LOGITS
    komple
    1.37
     humeur
    1.35
     jaunes
    1.35
    llllll
    1.32
     couverts
    1.31
    terape
    1.30
    sprzedam
    1.30
     arriver
    1.30
     作り方
    1.27
     écla
    1.26
    Activations Density 0.021%

    No Known Activations