© 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. 8767
    Prev
    Next
    INDEX
    Explanations

    have been past participle

    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
    er
    3.62
    る
    2.93
    ்
    2.91
    ה
    2.87
    oooooooo
    2.83
    ي
    2.75
    o
    2.66
    𝒍
    2.65
    ی
    2.64
    oooo
    2.60
    POSITIVE LOGITS
    ᴇ
    2.73
     sund
    2.70
    ность
    2.68
    ᴋ
    2.60
    =('
    2.45
     been
    2.34
    oksatta
    2.29
    ங்கிணை
    2.29
     mares
    2.28
    ᠨ
    2.27
    Activations Density 0.490%

    No Known Activations