© 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. 15490
    Prev
    Next
    INDEX
    Explanations

    code comments and separators

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

    The neuron is sensitive to numeric tokens (strings containing digits, such as decimal‐formatted numbers).

    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
     $=$
    0.52
     \%
    0.50
    a
    0.47
     $=
    0.47
    an
    0.46
    ad
    0.46
    at
    0.45
    ₂,
    0.42
     =,
    0.42
     $\$
    0.41
    POSITIVE LOGITS
    <unused2176>
    0.54
    क्ति
    0.53
    रुख
    0.50
    Ḫ
    0.50
     श्रद्धालुओं
    0.49
    <unused2154>
    0.49
     இருப்பினும்
    0.49
     Oberfläche
    0.49
     하지만
    0.48
     amenazas
    0.48
    Activations Density 0.070%

    No Known Activations