© 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. 163338
    Prev
    Next
    INDEX
    Explanations

    work, online, holiday, Facebook, philosophy, nature

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

    controls of attacker duct opinion inserts styles world

    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
    ربي
    0.49
    تما
    0.47
     Hiro
    0.46
     Javier
    0.46
    ራ
    0.45
     carga
    0.45
    وهات
    0.44
    احت
    0.44
     Mohd
    0.44
    %:
    0.44
    POSITIVE LOGITS
    у
    0.47
    Visitor
    0.44
     eye
    0.44
    opacity
    0.44
    speakers
    0.44
     ادب
    0.43
     বাঙ্গালীর
    0.43
     accidens
    0.43
    ymb
    0.43
     तीसरा
    0.43
    Activations Density 0.001%

    No Known Activations