© 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. 222449
    Prev
    Next
    INDEX
    Explanations

    long before, single alternative, lunch and dinner

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

    non english characters

    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
    পাশে
    0.53
    旁的
    0.46
     Decorative
    0.46
    μοί
    0.45
    ểu
    0.44
    旁
    0.44
    ்ப்பு
    0.43
    ável
    0.43
     பிரதி
    0.43
     Associations
    0.42
    POSITIVE LOGITS
     אותו
    0.52
     الساعة
    0.49
     المن
    0.48
     $\$
    0.48
     المنت
    0.47
    га
    0.47
     corto
    0.46
     ści
    0.46
     vyz
    0.46
    ๑
    0.46
    Activations Density 0.000%

    No Known Activations