© 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. 34-GEMMASCOPE-RES-131K
    7. 48202
    Prev
    Next
    INDEX
    Explanations

    slide show/slideshow

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

    The neuron fires on multi‐digit numeric tokens (e.g. slide IDs, large 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_34/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
    d
    -1.09
    0
    -1.08
    9
    -1.04
    na
    -0.96
    you
    -0.93
    as
    -0.91
    sen
    -0.88
    탱
    -0.84
    ведений
    -0.82
    AS
    -0.82
    POSITIVE LOGITS
    Slide
    1.55
     Slide
    1.48
     slide
    1.48
     slides
    1.45
     slid
    1.28
     Slides
    1.20
    manı
    1.16
    chuckles
    1.13
    slides
    1.12
    slide
    1.10
    Activations Density 0.009%

    No Known Activations