© 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. 60414
    Prev
    Next
    INDEX
    Explanations

    services and inquiries

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

    describing specific terms

    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
    ทยาลัย
    0.48
     Большая
    0.48
    ственных
    0.48
    ኚ
    0.47
     слова
    0.46
    exerc
    0.46
     британ
    0.44
     дана
    0.44
    🕸
    0.43
     বিশ
    0.43
    POSITIVE LOGITS
     Albu
    0.49
     apoyo
    0.48
     Tel
    0.47
     PN
    0.47
     Philos
    0.47
     AN
    0.46
     SIN
    0.46
     Okinawa
    0.44
     Abu
    0.44
     SUPPORT
    0.44
    Activations Density 0.000%

    No Known Activations