© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11517
    Prev
    Next
    INDEX
    Explanations

    states or unusual conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    빽
    1.20
    <0xB0>
    1.10
     TRANSFER
    1.09
    豊富な
    1.09
    攘
    1.07
    览
    1.06
     Sturgeon
    1.05
    鹏
    1.03
     RG
    1.02
     Slug
    1.02
    POSITIVE LOGITS
    Improvements
    1.19
    However
    1.19
    Improved
    1.18
    Due
    1.15
    Modified
    1.12
    improved
    1.08
     adaptar
    1.07
    Improving
    1.05
     قامت
    1.05
    但是我
    1.05
    Activations Density 0.000%

    No Known Activations