© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 193719
    Prev
    Next
    INDEX
    Explanations

    miniature hobby, Sandefjord, 3GP, puppies, champion takedowns, High Command, MPG

    np_acts-logits-general · gemini-2.5-flash-lite

    contrast or conclusion

    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_31_width_262k_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
    ak
    0.64
    ed
    0.60
    el
    0.54
    am
    0.54
    uj
    0.54
    .
    0.52
    le
    0.51
    av
    0.49
    ell
    0.49
    an
    0.48
    POSITIVE LOGITS
     अपराध
    0.52
    伥
    0.52
     émotion
    0.50
    磵
    0.48
    轳
    0.47
    ຄວາມ
    0.46
     فات
    0.46
     écart
    0.45
     emotions
    0.45
     चौथ
    0.45
    Activations Density 0.000%

    No Known Activations