© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14598
    Prev
    Next
    INDEX
    Explanations

    parse book or string

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

    The neuron is primarily detecting numeric tokens—measurements, figure/table references, section or identifier numbers, and similar digit‐based references.

    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
    ",'
    0.85
    ছে
    0.84
    ﻳ
    0.79
    蓽
    0.77
    льными
    0.77
    ছি
    0.75
    itudes
    0.75
    ская
    0.75
    ">%
    0.75
    เสมอ
    0.75
    POSITIVE LOGITS
    brokers
    0.86
    2
    0.81
    3
    0.75
    LAS
    0.74
     américains
    0.73
    4
    0.73
    BLACK
    0.73
    broker
    0.72
    MUSIC
    0.72
    COLOR
    0.71
    Activations Density 0.000%

    No Known Activations