© 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. 67094
    Prev
    Next
    INDEX
    Explanations

    technical setup and configuration

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

    This neuron selectively activates on numeric tokens (digits, decimal numbers, version numbers, etc.) 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
    S
    -1.27
     refusé
    -1.26
     ».
    -1.23
    οντας
    -1.21
    摂取
    -1.19
    ⌀
    -1.19
     «
    -1.18
    plusplus
    -1.12
     departamentos
    -1.11
     также
    -1.10
    POSITIVE LOGITS
    Mereka
    1.18
    Groet
    1.15
     châ
    1.13
     къде
    1.13
    Seni
    1.12
     белом
    1.10
    Remover
    1.09
    Recept
    1.08
     駅前
    1.06
     DIRECTOR
    1.05
    Activations Density 0.001%

    No Known Activations