© 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. 252516
    Prev
    Next
    INDEX
    Explanations

    osprey

    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
    e
    0.64
    i
    0.61
    in
    0.59
    بد
    0.57
    o
    0.55
    গ
    0.53
    به
    0.53
    automatic
    0.53
    every
    0.51
    ي
    0.51
    POSITIVE LOGITS
     чём
    0.52
    riterien
    0.51
    িশীল
    0.48
     удовле
    0.48
     splendor
    0.47
     மனதில்
    0.47
     частности
    0.45
     చక్క
    0.45
     сколько
    0.45
     medici
    0.45
    Activations Density 0.001%

    No Known Activations