© 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. 15885
    Prev
    Next
    INDEX
    Explanations

    examples, steps, lists, charts, or processes

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

    The neuron highlights mid‐to‐long content words that serve as key technical or thematic terms (e.g. “warnings,” “analysis,” “frequency,” “decision,” “Diet”).

    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
     brillo
    0.85
    se
    0.76
    ano
    0.75
    AZIONE
    0.75
    ཎ
    0.75
    ITION
    0.73
    ALSE
    0.71
    ris
    0.71
    io
    0.70
    so
    0.70
    POSITIVE LOGITS
     Integrate
    0.79
    ../../
    0.78
    }}}$
    0.77
    ../../../
    0.76
     Xem
    0.75
     Khark
    0.74
     Exel
    0.74
     परिवर्तन
    0.73
     Gayle
    0.73
    อดู
    0.73
    Activations Density 0.000%

    No Known Activations