© 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. 14811
    Prev
    Next
    INDEX
    Explanations

    end of world scenarios

    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
     bekl
    1.58
    嬸
    1.57
     grün
    1.56
    捌章
    1.47
    婶
    1.47
     댓글
    1.47
    柒章
    1.46
    ✚
    1.43
     düşük
    1.43
     Böl
    1.43
    POSITIVE LOGITS
    с
    1.28
    is
    1.18
    caused
    1.15
    idad
    1.14
     caused
    1.13
    чого
    1.13
    ร
    1.09
    ти
    1.05
    on
    1.04
    тим
    1.03
    Activations Density 0.001%

    No Known Activations