© 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. 117636
    Prev
    Next
    INDEX
    Explanations

    Discovery and multilingualism

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

    contrast and qualification

    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
     규칙
    0.50
    ją
    0.45
    ikiem
    0.45
    เป็นการ
    0.44
     отобра
    0.44
    ının
    0.44
     नियमों
    0.44
    ㅏ
    0.44
     دکھائی
    0.43
     правила
    0.43
    POSITIVE LOGITS
     Indien
    0.49
    აზე
    0.43
    ल्डेन
    0.42
    ಕೆ
    0.42
    BAI
    0.41
    यरी
    0.41
    ناو
    0.41
     Loyal
    0.41
     outlets
    0.40
    ڈین
    0.40
    Activations Density 0.000%

    No Known Activations