© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1827
    Prev
    Next
    INDEX
    Explanations

    parentheses and slashes

    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
    菲
    0.88
     próximas
    0.87
    ̀ng
    0.87
    接到
    0.86
     yaşında
    0.86
    昶
    0.85
    masının
    0.84
     metà
    0.84
    又要
    0.83
    ఠ
    0.82
    POSITIVE LOGITS
    damage
    1.09
    footnote
    1.07
     Destruction
    1.06
    antal
    1.06
     invented
    1.05
    riture
    1.05
    ancy
    1.03
    prog
    1.03
    considering
    1.03
     जोखिम
    1.03
    Activations Density 0.199%

    No Known Activations