© 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. 14925
    Prev
    Next
    INDEX
    Explanations

    contextual modifiers or specific topics

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

    This neuron detects named entities, especially organization names, titles, and other proper nouns.

    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
    ني
    1.06
    唯一
    0.98
    ವೂ
    0.98
    ל
    0.95
    ssss
    0.94
    streets
    0.93
    november
    0.93
    st
    0.92
    おります
    0.92
    ם
    0.91
    POSITIVE LOGITS
    ;
    1.05
    ści
    1.00
    ein
    0.94
    ez
    0.91
     cryptography
    0.89
     관련된
    0.89
     teorie
    0.89
    \},
    0.88
    ïde
    0.88
     \%,
    0.87
    Activations Density 8.286%

    No Known Activations