© 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. 136378
    Prev
    Next
    INDEX
    Explanations

    claim, bearish, services, motorcycle, cute, directed, seeing, choice, blues

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

    technical trading charts

    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
     nesta
    0.53
    ুস
    0.52
     tady
    0.51
     moje
    0.51
    哴
    0.50
    丝
    0.49
    или
    0.48
    ্থ
    0.47
     Norwich
    0.47
     coloquei
    0.47
    POSITIVE LOGITS
    chas
    0.56
    cha
    0.54
    iby
    0.53
    i
    0.52
    fra
    0.49
    strap
    0.49
    pattern
    0.49
    meme
    0.49
    casts
    0.48
    chart
    0.48
    Activations Density 0.000%

    No Known Activations