© 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. 136731
    Prev
    Next
    INDEX
    Explanations

    US state abbreviations (OH, MN, NY)

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

    choose / choosing / use

    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
    氲
    0.49
    罨
    0.49
     படங்களில்
    0.48
    ادی
    0.47
     meriye
    0.46
     پیدا
    0.46
    ств
    0.46
    روع
    0.45
     soğ
    0.45
    䡉
    0.45
    POSITIVE LOGITS
    4
    0.64
    five
    0.63
    3
    0.62
    6
    0.61
    5
    0.61
    1
    0.57
     five
    0.55
    whereas
    0.52
    7
    0.52
    value
    0.51
    Activations Density 0.000%

    No Known Activations