© 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. 12-GEMMASCOPE-2-RES-16K
    7. 462
    Prev
    Next
    INDEX
    Explanations

    new beginnings

    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_12_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
    ó
    1.72
    ating
    1.34
    TimeStamp
    1.34
    ר
    1.30
    ően
    1.27
    ighed
    1.25
    ển
    1.23
    তিনি
    1.23
    onomy
    1.23
    entas
    1.23
    POSITIVE LOGITS
     exons
    1.66
    स
    1.47
    ти
    1.45
     appellants
    1.45
     immunoblot
    1.41
     hostilities
    1.40
     envo
    1.40
    ్
    1.39
     happenings
    1.36
    те
    1.31
    Activations Density 0.809%

    No Known Activations