© 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. 5271
    Prev
    Next
    INDEX
    Explanations

    direction change

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

    The neuron strongly fires on mid‐sentence capitalized words—i.e. proper names and other named entities.

    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
    ло
    0.93
    hip
    0.86
    ти
    0.86
    ної
    0.84
    ifred
    0.83
    чів
    0.83
    تی
    0.81
    umo
    0.81
    podob
    0.81
    вні
    0.80
    POSITIVE LOGITS
     angeles
    0.86
     vans
    0.78
     ose
    0.78
     vanaf
    0.76
     డి
    0.75
    壽
    0.74
     ontst
    0.73
     coasters
    0.73
     geen
    0.73
     oors
    0.73
    Activations Density 0.000%

    No Known Activations