© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2572
    Prev
    Next
    INDEX
    Explanations

    computational processing phrases

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

    The main thing this neuron does is pick out longer-content words (i.e. tokens of greater length).

    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
     kiddos
    0.80
     heartbreak
    0.71
     standout
    0.70
    0.69
     nhé
    0.68
    e
    0.68
    0
    0.67
     smiley
    0.66
     impactful
    0.65
     Kayla
    0.65
    POSITIVE LOGITS
     intensively
    0.71
    📡
    0.68
    制御
    0.68
     машиналары
    0.66
     مراکز
    0.66
     主要
    0.66
     システム
    0.66
     pathogenesis
    0.64
     dynamism
    0.64
    প্রধান
    0.63
    Activations Density 2.021%

    No Known Activations