© 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. 56925
    Prev
    Next
    INDEX
    Explanations

    future, latest, courses

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

    analyzing options and statements

    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
     NAME
    0.48
    บุรี
    0.48
    楨
    0.46
     METHODS
    0.46
     bhavanti
    0.44
    ρή
    0.43
    NAME
    0.42
    સિ
    0.42
     আলি
    0.42
     नाम
    0.41
    POSITIVE LOGITS
    d
    0.54
    r
    0.49
    rpt
    0.48
    herent
    0.48
     صاف
    0.47
     Ан
    0.46
    herence
    0.45
     Mascul
    0.45
    imed
    0.44
     Dla
    0.44
    Activations Density 0.000%

    No Known Activations