© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16331
    Prev
    Next
    INDEX
    Explanations

    in phrases like "in this"

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

    The neuron detects and flags standalone 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
    鋌
    -1.27
     from
    -1.23
     таблетки
    -1.20
    jét
    -1.19
     and
    -1.17
    lijken
    -1.15
     だっ
    -1.13
     músculos
    -1.13
    "+"
    -1.13
    ducers
    -1.10
    POSITIVE LOGITS
    そして
    1.34
    completely
    1.05
    Moreover
    1.03
     locura
    1.02
    什么呢
    1.02
     hecho
    1.01
     durante
    0.99
    полне
    0.99
     it
    0.99
    ronic
    0.99
    Activations Density 0.069%

    No Known Activations