© 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. 247580
    Prev
    Next
    INDEX
    Explanations

    line separators and placeholders

    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
     ಸ್ನೇಹಿತ
    0.58
     بيد
    0.56
     賞
    0.54
     പരിച
    0.54
     сердце
    0.53
     вклю
    0.52
     لوبې
    0.52
     شام
    0.52
     здійс
    0.52
     wak
    0.51
    POSITIVE LOGITS
    0.52
    ลาด
    0.52
    {
    0.51
    0
    0.50
     Are
    0.49
    εργ
    0.48
    ισ
    0.47
    strip
    0.47
    ppo
    0.46
    import
    0.46
    Activations Density 0.002%

    No Known Activations