© 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. 14374
    Prev
    Next
    INDEX
    Explanations

    or as options

    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
    各项
    1.15
     everyone
    1.14
    <unused1656>
    1.13
    шла
    1.12
    アンド
    1.10
    IPOP
    1.10
     মহাশয়
    1.09
    暨
    1.09
    <unused1201>
    1.06
    സും
    1.06
    POSITIVE LOGITS
     or
    4.89
     oder
    4.75
     или
    4.69
    或
    4.44
     atau
    4.35
     hoặc
    4.30
    或者
    4.28
    หรือ
    4.25
    或是
    4.24
     либо
    4.17
    Activations Density 1.203%

    No Known Activations