© 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. 188448
    Prev
    Next
    INDEX
    Explanations

    keywords, phrases, and lists

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

    keywords following punctuation

    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
     allerlei
    0.50
     Normalmente
    0.44
     ها
    0.43
    '=>'','
    0.42
     `:`,
    0.42
     પ્રેમ
    0.41
     hôtel
    0.41
     libros
    0.40
     பணம்
    0.40
     എന്നാല്‍
    0.38
    POSITIVE LOGITS
     కూడా
    0.50
    ALSO
    0.43
    ։
    0.42
    বর্ধ
    0.42
    Also
    0.41
    ปาก
    0.41
    🌛
    0.41
    also
    0.40
    这也
    0.40
    🔟
    0.40
    Activations Density 0.006%

    No Known Activations