© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 163803
    Prev
    Next
    INDEX
    Explanations

    first or specific ordinal

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

    impl followed by type

    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
    你也
    0.50
     మీకు
    0.45
     менедже
    0.44
    િ
    0.42
    跟你
    0.42
    тал
    0.42
    წი
    0.41
    ത
    0.41
    리와
    0.41
    лах
    0.40
    POSITIVE LOGITS
     Empor
    0.46
     ਜੋ
    0.44
     จัก
    0.43
     Necessary
    0.42
     intense
    0.41
     inorder
    0.41
     parochial
    0.41
     robust
    0.41
     विकार
    0.40
    すなわち
    0.40
    Activations Density 0.000%

    No Known Activations