© 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. 197046
    Prev
    Next
    INDEX
    Explanations

    proper nouns and entities

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

    description and institutions

    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
     學
    0.59
    ।"
    0.52
     +.
    0.52
    ।'
    0.52
     Фер
    0.52
     प्लस
    0.51
     플러스
    0.51
     하지
    0.51
     П
    0.50
     Фе
    0.50
    POSITIVE LOGITS
    də
    0.47
    医生
    0.46
    Chhattisgarh
    0.46
    MIT
    0.45
    Pitts
    0.45
    Government
    0.44
    いや
    0.43
    曼
    0.43
    Lok
    0.43
    一个
    0.42
    Activations Density 0.000%

    No Known Activations