© 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. 95895
    Prev
    Next
    INDEX
    Explanations

    powerful requested Prompt

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

    dark humor, streaming numbers, bits

    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
    아
    0.52
    л
    0.51
    inees
    0.49
    ק
    0.48
     простых
    0.47
    이
    0.47
    の大
    0.46
    к
    0.46
    하는
    0.46
     кіль
    0.46
    POSITIVE LOGITS
     stolen
    0.44
    ോഷ്യ
    0.44
     mémoire
    0.42
     રંગ
    0.41
     സമയം
    0.41
     Nietzsche
    0.40
     बनर्जी
    0.40
    ப்பதற்காக
    0.39
     मुख्यतः
    0.39
     Hanging
    0.39
    Activations Density 0.000%

    No Known Activations