© 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. 12070
    Prev
    Next
    INDEX
    Explanations

    code execution and timing

    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
    𝕤
    0.83
    боли
    0.78
    маш
    0.77
     ､
    0.77
     хі
    0.76
    ни
    0.75
    бто
    0.75
    нил
    0.74
    ţional
    0.73
     видно
    0.73
    POSITIVE LOGITS
    be
    0.96
    h
    0.86
    me
    0.78
    ac
    0.75
    hab
    0.74
     Verhalten
    0.74
     erfolgre
    0.73
    seconds
    0.71
    hn
    0.71
     ikinci
    0.71
    Activations Density 0.001%

    No Known Activations