© 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. 68720
    Prev
    Next
    INDEX
    Explanations

    construction debris

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

    ability to communicate outcomes

    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
    ಆ
    0.48
    хі
    0.48
    Formal
    0.47
    쯔
    0.47
    ಕ್ಕೂ
    0.46
    uggling
    0.46
    Vaterpolo
    0.46
    甜蜜
    0.45
    اہد
    0.45
    レポート
    0.44
    POSITIVE LOGITS
     Universal
    0.52
     Deutschen
    0.47
     {\
    0.47
     occult
    0.46
     refurbished
    0.46
     trams
    0.45
     Sz
    0.45
     Physi
    0.45
     latino
    0.44
     скажу
    0.44
    Activations Density 0.001%

    No Known Activations