© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13535
    Prev
    Next
    INDEX
    Explanations

    nature, fabric, volume

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

    This neuron responds to emphatic adjectives that signal magnitude or importance (e.g., “vast,” “significant,” “sheer”).

    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_31_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
    iosamente
    0.75
     Про
    0.71
     як
    0.71
     メンズ
    0.71
    ország
    0.70
     개의
    0.70
     পুস্তকের
    0.70
    ⌯
    0.69
    fragen
    0.69
    handedly
    0.66
    POSITIVE LOGITS
     confines
    1.25
     entirety
    1.19
     plight
    1.14
     meisten
    1.12
     intricacies
    1.12
     remainder
    1.09
     scourge
    1.09
     adage
    1.08
     extent
    1.04
     expanse
    1.03
    Activations Density 0.802%

    No Known Activations