© 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. 69956
    Prev
    Next
    INDEX
    Explanations

    check range

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

    school subjects and roles

    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
    দৃশ্য
    0.46
    評
    0.43
    र्‍या
    0.43
     FEC
    0.43
     конструк
    0.43
     упо
    0.42
     ряд
    0.42
    大多數
    0.41
     adequacy
    0.41
    舴
    0.41
    POSITIVE LOGITS
    然后在
    0.49
     በኋላ
    0.45
     forehead
    0.44
     álgebra
    0.44
     baad
    0.43
    clerc
    0.43
     وبعد
    0.42
    gh
    0.42
    𝚗
    0.42
    erten
    0.41
    Activations Density 0.001%

    No Known Activations