© 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. 64698
    Prev
    Next
    INDEX
    Explanations

    independent Palestinian

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

    quantum gravity

    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
    哥哥
    0.49
     ото
    0.48
    그
    0.47
    собен
    0.45
     confronts
    0.45
     longest
    0.44
     remem
    0.43
    <unused2078>
    0.43
     ხ
    0.42
     чу
    0.42
    POSITIVE LOGITS
     Confidential
    0.64
     Dunes
    0.53
     Parallel
    0.50
     clandestine
    0.49
     ETA
    0.49
     Microscopy
    0.49
     FTP
    0.48
     KCl
    0.48
     WW
    0.48
     Tables
    0.47
    Activations Density 0.000%

    No Known Activations