© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 21136
    Prev
    Next
    INDEX
    Explanations

    bunch of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
     to
    1.64
    H
    1.37
    can
    1.27
    been
    1.20
    C
    1.18
    P
    1.16
    A
    1.15
     s
    1.14
    with
    1.14
    G
    1.14
    POSITIVE LOGITS
    ले
    1.14
    يد
    1.05
     of
    1.03
    ’
    1.02
    ית
    0.98
    يف
    0.95
    లో
    0.94
    ”
    0.91
    يل
    0.90
    ிக்க
    0.88
    Activations Density 0.013%

    No Known Activations