© 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. 11729
    Prev
    Next
    INDEX
    Explanations

    Use if

    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
    al
    2.79
     die
    2.50
    ت
    2.14
    ی
    2.10
    ..</
    2.10
    방
    2.02
    ..
    2.02
    ing
    2.01
    orient
    1.96
    ar
    1.94
    POSITIVE LOGITS
    گز
    3.20
     ['<%=
    3.15
    сторія
    3.05
    strij
    2.96
     नर्म
    2.93
     Ам
    2.87
    ВА
    2.84
     Trời
    2.80
    Читати
    2.79
    बेस
    2.79
    Activations Density 0.020%

    No Known Activations