© 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. 156536
    Prev
    Next
    INDEX
    Explanations

    show to services treatment great art foregoing children

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

    zip, exists, secrets, Verse, 4, legal, CK

    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
    HT
    0.51
    j
    0.47
     Ka
    0.47
    HU
    0.45
    ai
    0.45
    AR
    0.44
    রোধ
    0.43
    ER
    0.43
    亟
    0.43
     Lag
    0.43
    POSITIVE LOGITS
    ಂಕ
    0.54
    veillance
    0.47
    писание
    0.46
     цену
    0.46
     binatang
    0.46
    бин
    0.46
     бен
    0.45
     세상
    0.45
     parum
    0.45
     ф
    0.45
    Activations Density 0.000%

    No Known Activations