© 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. 3420
    Prev
    Next
    INDEX
    Explanations

    instead,

    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
    a
    2.01
    as
    1.73
    al
    1.69
     owners
    1.66
     c
    1.63
    an
    1.63
    o
    1.62
    া
    1.59
     india
    1.59
     houses
    1.57
    POSITIVE LOGITS
    ᡧ
    2.02
    လိုအပ်
    1.98
    utations
    1.94
    की
    1.93
    ಯಲ್ಲಿ
    1.92
    َق
    1.91
    いる
    1.90
     نړ
    1.90
    ЕТ
    1.88
    úč
    1.87
    Activations Density 0.022%

    No Known Activations