© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199252
    Prev
    Next
    INDEX
    Explanations

    technical installation descriptions

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

    in practice, often used synonymously

    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
    Negative Logits
    Ω
    0.47
    >≤</
    0.46
    ある
    0.45
    چھ
    0.45
    定番
    0.45
    こだわ
    0.45
    Hannah
    0.45
    เล
    0.45
     ตาย
    0.44
    =#
    0.43
    POSITIVE LOGITS
     inserting
    0.45
     हरकत
    0.45
     Entonces
    0.44
    ěř
    0.42
    hesk
    0.42
     вмеша
    0.42
     nuest
    0.40
     пул
    0.40
    ச்ச
    0.39
     técn
    0.39
    Activations Density 0.000%

    No Known Activations