© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13955
    Prev
    Next
    INDEX
    Explanations

    request

    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_31_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
    য়া
    0.80
    는
    0.71
    -
    0.68
    لم
    0.64
     dục
    0.64
    ковский
    0.63
    '
    0.63
    ají
    0.63
    是
    0.62
     iyo
    0.62
    POSITIVE LOGITS
    d
    1.22
     Request
    1.07
     Requests
    0.98
    Request
    0.94
    b
    0.90
    request
    0.89
    as
    0.87
    an
    0.86
    on
    0.84
    AnimationFrame
    0.84
    Activations Density 0.116%

    No Known Activations