© 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. 133286
    Prev
    Next
    INDEX
    Explanations

    official files and notifications

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

    official titles and historical figures

    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
     działania
    0.52
     મોત
    0.50
     уби
    0.47
    Ḍ
    0.47
    കർ
    0.47
     doğrud
    0.47
     gangguan
    0.45
    ฒ
    0.45
     payback
    0.45
     പ്രവർത്തി
    0.44
    POSITIVE LOGITS
    '
    0.61
     to
    0.53
     Priv
    0.50
    পত্রের
    0.50
    主要
    0.50
    ous
    0.49
     files
    0.49
     official
    0.49
    files
    0.49
    0.48
    Activations Density 0.001%

    No Known Activations