© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10092
    Prev
    Next
    INDEX
    Explanations

    many apples | spelled Þrymr | the difference | applied

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

    The neuron fires on keywords and headings commonly used in formal instructions, guidelines, or terms‐of‐service–style passages.

    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
     ใช่
    0.91
    າ
    0.85
     enemigos
    0.84
    ﻞ
    0.84
     clipart
    0.84
    ouer
    0.84
    τερ
    0.83
     hemen
    0.82
     vjer
    0.82
    ﻦ
    0.81
    POSITIVE LOGITS
     ро
    0.74
    il
    0.69
     appunto
    0.67
     risc
    0.66
     PMC
    0.66
     partly
    0.65
    <0x9F>
    0.64
    ەکە
    0.64
     difíc
    0.64
    影像
    0.63
    Activations Density 0.000%

    No Known Activations