© 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. 81352
    Prev
    Next
    INDEX
    Explanations

    times or duration, specific events

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

    investment, international, sophisticated

    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
     بیم
    0.47
    IVING
    0.44
     বিশ্রাম
    0.44
     ກ
    0.44
     黄
    0.44
     பா
    0.43
     बजकर
    0.43
     های
    0.43
     パン
    0.42
     yapılacak
    0.42
    POSITIVE LOGITS
    ವೇಂದ್ರ
    0.49
    ेंटीना
    0.43
    材質
    0.42
     jeweler
    0.42
    حديد
    0.41
    우스
    0.41
     দার্শন
    0.41
    蝼
    0.41
     দার্শনিক
    0.40
     newer
    0.40
    Activations Density 0.001%

    No Known Activations