© 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. 487
    Prev
    Next
    INDEX
    Explanations

    numbers, indices, positions

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

    The neuron is primarily detecting numeric literals (especially floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    line breaks or newlines in code or technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    code comment and documentation sections within source code or technical scripts

    oai_token-act-pair · gpt-5Triggered 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
     be
    0.23
     so
    0.23
     of
    0.22
    ↵↵
    0.21
     are
    0.21
    že
    0.20
     Americana
    0.20
     jiné
    0.20
     in
    0.20
     do
    0.20
    POSITIVE LOGITS
    SanPham
    0.24
     ヘ
    0.24
    YAML
    0.23
     ニット
    0.22
    رسٹ
    0.22
     ))->
    0.22
    OUBLE
    0.22
    пили
    0.21
    ╽
    0.21
    ヤモンド
    0.21
    Activations Density 0.003%

    No Known Activations