© 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. 8896
    Prev
    Next
    INDEX
    Explanations

    application fields

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

    The neuron detects highly detailed technical specification language describing product features (e.g. waterproof ratings and usage details).

    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
    ١
    0.91
    苺
    0.91
    拵
    0.91
    Graphs
    0.90
    誂
    0.89
    ۱
    0.88
    Barnes
    0.87
    Fitz
    0.87
    Wyn
    0.85
     بڑھ
    0.84
    POSITIVE LOGITS
     comprehensively
    1.17
     moisturizing
    1.10
     netizens
    1.10
     hemolysis
    1.09
     adsorption
    1.08
     volatil
    1.05
     yuan
    1.05
     、
    1.02
     domine
    1.01
     meritorious
    1.01
    Activations Density 0.197%

    No Known Activations