© 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. 7551
    Prev
    Next
    INDEX
    Explanations

    document types that present information

    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
     captivating
    1.24
     conclusive
    1.15
     concluded
    1.10
     compelling
    1.10
     conclusively
    1.06
     comprehensively
    1.05
    <unused747>
    1.03
    كد
    1.03
     guarantee
    1.02
     स्टेटमेंट
    1.02
    POSITIVE LOGITS
    بعض
    0.64
     هنگام
    0.64
    一些
    0.61
    Small
    0.61
    Normalization
    0.60
     p
    0.59
    前の
    0.59
     بعض
    0.59
    Some
    0.59
     nếu
    0.58
    Activations Density 0.026%

    No Known Activations