© 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. 9011
    Prev
    Next
    INDEX
    Explanations

    GW, snapshot, primes, slice

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

    This neuron strongly activates on infrequent, content‐bearing full words (i.e. longer whole‐word tokens) rather than common subword fragments or punctuation.

    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
    Tính
    0.73
    Wenn
    0.68
    Favorite
    0.68
    Hot
    0.68
    如果你
    0.66
     intuitive
    0.66
    3
    0.65
    Serialized
    0.64
    Sample
    0.64
     بص
    0.63
    POSITIVE LOGITS
     Paragu
    0.87
     ঘরের
    0.82
     Compiler
    0.81
    瘍
    0.80
     discorso
    0.80
     しかし
    0.79
     파
    0.79
     Capacitor
    0.79
    tudo
    0.78
    鷸
    0.78
    Activations Density 0.001%

    No Known Activations