© 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. 149280
    Prev
    Next
    INDEX
    Explanations

    mathematics, health, sports, medical, writing, arts

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

    running first analysis

    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
    0
    0.64
    .
    0.57
    5
    0.57
    2
    0.57
    N
    0.55
    db
    0.55
    s
    0.55
    ed
    0.54
    edu
    0.53
    1
    0.52
    POSITIVE LOGITS
     imasmim
    0.59
     किल्ला
    0.59
     選
    0.54
     鳥
    0.54
     መድሃኒ
    0.53
     attham
    0.52
    樍
    0.52
     Ettha
    0.52
     Tattha
    0.51
     реализу
    0.51
    Activations Density 0.000%

    No Known Activations