© 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. 21504
    Prev
    Next
    INDEX
    Explanations

    also known as

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

    also known as / or

    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
    ۲
    0.43
    ۹
    0.40
    archiwizowane
    0.39
     கண்டிப்பாக
    0.39
    ொள்ள
    0.38
    ۆی
    0.38
     ficando
    0.38
     ඒවා
    0.37
    schnitt
    0.37
    २
    0.37
    POSITIVE LOGITS
     alebo
    0.60
     किंवा
    0.59
     because
    0.58
     veya
    0.56
     లేదా
    0.55
     или
    0.54
     ataupun
    0.54
     또는
    0.53
    或者是
    0.52
     or
    0.52
    Activations Density 0.065%

    No Known Activations