© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3327
    Prev
    Next
    INDEX
    Explanations

    LMS, acronyms ending in PS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    3.27
    to
    3.23
    tions
    3.23
    tion
    3.03
    the
    2.97
    table
    2.89
    ti
    2.83
    tr
    2.75
    times
    2.67
    takes
    2.64
    POSITIVE LOGITS
    ن
    2.80
    itating
    2.30
    ה
    2.25
    س
    2.23
    ם
    2.19
    ̌
    2.16
    ول
    2.13
    ح
    2.13
    بي
    2.11
    ك
    2.03
    Activations Density 0.689%

    No Known Activations