© 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. 135102
    Prev
    Next
    INDEX
    Explanations

    easy to

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

    updates, changes, bounty, or Alaskan

    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
     parameter
    0.46
     highScore
    0.46
     nb
    0.46
     тради
    0.45
     you
    0.44
     दौड़
    0.43
    శ
    0.43
     ч
    0.43
    णाल
    0.42
     teenager
    0.42
    POSITIVE LOGITS
     gacche
    0.55
    λος
    0.49
    VP
    0.46
     сот
    0.46
    lays
    0.46
    Bart
    0.45
    pción
    0.43
    ле
    0.43
    lists
    0.43
    fisherman
    0.43
    Activations Density 0.000%

    No Known Activations