© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4533
    Prev
    Next
    INDEX
    Explanations

    word origin and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Васи
    0.92
    idmat
    0.90
    <unused624>
    0.90
     ያስፈል
    0.89
     внед
    0.89
     सूर
    0.88
     hidrául
    0.87
     matrícula
    0.86
    <unused1992>
    0.85
     }()
    0.85
    POSITIVE LOGITS
     seem
    0.85
     seems
    0.82
     seemed
    0.79
     appear
    0.77
     appears
    0.75
     subtle
    0.74
     subtly
    0.71
     seeming
    0.71
     actually
    0.70
    చు
    0.70
    Activations Density 0.023%

    No Known Activations