© 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-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 13
    Prev
    Next
    INDEX
    Explanations

    questions, instructions, or commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_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
    ка
    0.48
    5
    0.45
    .
    0.43
    त
    0.42
    :
    0.42
    '
    0.41
    و
    0.41
    AR
    0.39
    sa
    0.38
    Если
    0.38
    POSITIVE LOGITS
     to
    0.38
     be
    0.35
     a
    0.34
     was
    0.32
     నే
    0.31
     of
    0.30
    ্বরূপ
    0.28
    ರಳ
    0.28
     it
    0.27
    ियों
    0.27
    Activations Density 0.381%

    No Known Activations