© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7685
    Prev
    Next
    INDEX
    Explanations

    high praise, excellent descriptions

    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
     nagyon
    0.54
     rất
    0.53
     매우
    0.53
     прият
    0.52
     veľmi
    0.51
     👍
    0.48
    非常好
    0.48
     дуже
    0.47
     очень
    0.47
     veldig
    0.47
    POSITIVE LOGITS
    '
    0.56
    ln
    0.42
    d
    0.37
     seeking
    0.37
    w
    0.36
    t
    0.36
    is
    0.36
    ası
    0.35
     কিংবা
    0.34
    _
    0.34
    Activations Density 0.046%

    No Known Activations