© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7292
    Prev
    Next
    INDEX
    Explanations

    hydrolysis aqueous osmotic oceanic tropics

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     профессиона
    0.70
     paparazzi
    0.69
     Millennials
    0.65
    ℎ
    0.65
     unclaimed
    0.64
    ɦ
    0.64
     unprofessional
    0.63
     scammers
    0.63
    ͋
    0.63
    ừa
    0.62
    POSITIVE LOGITS
     osmotic
    0.74
     Mediterranean
    0.71
    Mediterranean
    0.71
     Balkans
    0.69
     tropics
    0.67
     जैव
    0.67
     geochemical
    0.67
     eastward
    0.66
     cairan
    0.66
     Ammonium
    0.64
    Activations Density 0.032%

    No Known Activations