© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8429
    Prev
    Next
    INDEX
    Explanations

    resignation, readiness, criteria, safety, empirical quantile

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

    This neuron detects numeric tokens (especially volume, page, and other citation numbers) in bibliographic or technical listings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    T
    0.91
    u
    0.89
    F
    0.88
    A
    0.86
    L
    0.80
    i
    0.78
    D
    0.78
    C
    0.75
    proc
    0.73
    )}+
    0.73
    POSITIVE LOGITS
     tumultuous
    0.96
     grapefruit
    0.93
     intimidation
    0.93
     vows
    0.91
     triglyceride
    0.89
     luôn
    0.88
     rectal
    0.88
     custard
    0.88
     clowns
    0.87
    ೀವ
    0.86
    Activations Density 0.000%

    No Known Activations