© 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. 10-GEMMASCOPE-RES-131K
    7. 86488
    Prev
    Next
    INDEX
    Explanations

    scanned page references

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

    The neuron activates on numeric tokens (integers or decimals), marking values like page numbers, gains, frequencies, or other measurements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     a
    -1.53
     the
    -1.47
     this
    -1.42
    ARROLL
    -1.41
     vardı
    -1.39
    #%%
    -1.37
     primeiros
    -1.34
     ngừa
    -1.34
    providedIn
    -1.32
     from
    -1.30
    POSITIVE LOGITS
    Its
    1.55
    asties
    1.41
     После
    1.41
    攫
    1.40
     различни
    1.39
     its
    1.36
     Vielzahl
    1.35
    ppled
    1.34
    тій
    1.34
     kaca
    1.30
    Activations Density 0.008%

    No Known Activations