© 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. 10828
    Prev
    Next
    INDEX
    Explanations

    seeing visual changes

    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
    ittle
    2.46
    <i>
    2.46
    '
    2.36
    <b>
    2.09
    чать
    2.06
    ..."
    2.00
    쪽에
    1.97
    حية
    1.97
    굴
    1.97
    른
    1.96
    POSITIVE LOGITS
    ׁ
    3.29
    ోతి
    3.12
    пециа
    3.02
    ો
    3.01
     linear
    2.98
    clud
    2.98
    ता
    2.97
     Refs
    2.89
     acqua
    2.87
     Alamo
    2.86
    Activations Density 0.006%

    No Known Activations