© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11213
    Prev
    Next
    INDEX
    Explanations

    you won't believe

    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_7_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
    ት
    2.19
    ीट
    2.12
    роприя
    2.12
    тельно
    2.08
    нет
    2.06
    ilmente
    2.05
    ו
    2.05
    otopy
    2.04
    utdown
    2.03
    स्त्रा
    2.02
    POSITIVE LOGITS
    SI
    1.75
     ).
    1.72
    이며
    1.60
    های
    1.56
    ).
    1.54
     I
    1.53
    .)
    1.49
    처
    1.47
     ;
    1.46
    이지만
    1.44
    Activations Density 0.000%

    No Known Activations