© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2770
    Prev
    Next
    INDEX
    Explanations

    Here's a breakdown

    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
     numai
    1.13
     kammam
    1.11
     endExpNow
    1.07
    朿
    1.03
    <unused830>
    1.03
     tikai
    1.02
    郄
    1.00
     razy
    1.00
    Хар
    0.99
     এডিনবার্গ
    0.99
    POSITIVE LOGITS
     F
    1.06
    ↵↵
    1.03
     My
    1.03
     As
    1.02
     On
    0.99
     The
    0.97
     A
    0.97
     Like
    0.97
     Note
    0.96
     What
    0.95
    Activations Density 0.455%

    No Known Activations