© 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. 131899
    Prev
    Next
    INDEX
    Explanations

    followed by "for" or "."

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

    Indian currency and government entities

    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
    ДЕ
    0.53
    珹
    0.53
    Глав
    0.52
    レディース
    0.51
    ถาน
    0.48
     यमुना
    0.47
    Все
    0.47
    आधी
    0.46
    Да
    0.45
    ⚋
    0.44
    POSITIVE LOGITS
     eyelid
    0.54
     risked
    0.53
     risking
    0.51
     laparoscopic
    0.51
     furnishing
    0.50
     enclosing
    0.50
    uff
    0.49
     pore
    0.48
     nourishment
    0.48
     submits
    0.48
    Activations Density 0.000%

    No Known Activations