© 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. 155725
    Prev
    Next
    INDEX
    Explanations

    Explain specific contexts for files

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

    shortest path

    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
    지
    0.56
    kA
    0.50
    刓
    0.47
    廠商
    0.46
     provincia
    0.46
    海拔
    0.46
    ֿ
    0.46
    㗆
    0.46
     अत्या
    0.46
     Provincia
    0.46
    POSITIVE LOGITS
    primer
    0.46
    privacy
    0.45
    ChooseServer
    0.44
    Rang
    0.44
    JMenuItem
    0.44
    MDEwOlJlcG
    0.44
    pyrid
    0.43
    ObjectID
    0.43
    randomIndex
    0.43
    közi
    0.43
    Activations Density 0.000%

    No Known Activations