© 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. 131352
    Prev
    Next
    INDEX
    Explanations

    th anniversary, consistent basis

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

    launched when, but, bit

    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
    ו
    0.52
     ការ
    0.47
    にとっては
    0.46
    КА
    0.46
    п
    0.44
     trousers
    0.44
    வரது
    0.44
    Agence
    0.44
    ｺ
    0.43
    Constr
    0.43
    POSITIVE LOGITS
    if
    0.49
     if
    0.44
     BMP
    0.43
    大家好
    0.43
     Midway
    0.43
     البح
    0.43
    elakaan
    0.43
    穿越
    0.42
     Handles
    0.42
    春节
    0.42
    Activations Density 0.000%

    No Known Activations