© 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. 206122
    Prev
    Next
    INDEX
    Explanations

    many years

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

    technical and precise language

    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
     dominions
    0.48
     theorists
    0.48
    ERN
    0.47
     ทุก
    0.47
     currentIndex
    0.47
     obsz
    0.46
     independientes
    0.46
    }^{+}\
    0.46
    gleichen
    0.45
     doodles
    0.44
    POSITIVE LOGITS
    ক্ষার
    0.50
    RUNTIME
    0.46
    ---
    0.44
    졌다
    0.44
     Lupus
    0.44
     Augusta
    0.44
    बिग
    0.44
    ார்க
    0.43
    为了
    0.43
    었습니다
    0.43
    Activations Density 0.001%

    No Known Activations