© 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. 39806
    Prev
    Next
    INDEX
    Explanations

    pop up tents

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

    The neuron activates primarily on numeric tokens (multi‐digit numbers) throughout 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
     ऐप
    -1.34
    czu
    -1.19
    笤
    -1.16
     bebes
    -1.13
     mej
    -1.13
     İç
    -1.13
    чня
    -1.12
    Луч
    -1.11
     granito
    -1.10
    ஏ
    -1.10
    POSITIVE LOGITS
    4
    1.41
    3
    1.40
    6
    1.23
    5
    1.21
    9
    1.19
     hingga
    1.18
     to
    1.09
    7
    1.08
     другим
    1.05
    2
    1.03
    Activations Density 0.015%

    No Known Activations