© 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. 107186
    Prev
    Next
    INDEX
    Explanations

    credit restoration and savings

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

    adapt, divisible, mother

    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
     stricter
    0.50
    marriage
    0.46
    नाडा
    0.46
     poorer
    0.46
    ၸ
    0.46
    massage
    0.46
    ॉरिटी
    0.45
    豆
    0.45
     टॉप
    0.45
    ५
    0.44
    POSITIVE LOGITS
    andı
    0.47
     cosmological
    0.46
     Änderungen
    0.46
    ებისთვის
    0.45
     dissected
    0.45
     ACB
    0.45
     modellen
    0.44
    红色
    0.44
    ARDS
    0.43
    ARING
    0.42
    Activations Density 0.000%

    No Known Activations