© 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. 3356
    Prev
    Next
    INDEX
    Explanations

    javascript function wrappers

    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
     bawah
    1.96
     menghasilkan
    1.86
     Thal
    1.82
     ①
    1.78
     jelas
    1.77
     Pacífico
    1.77
     giá
    1.72
    mina
    1.72
     gare
    1.72
     berp
    1.71
    POSITIVE LOGITS
    ت
    2.10
    ი
    2.09
    et
    2.05
    dS
    1.98
    ی
    1.92
    ാ
    1.84
    ej
    1.83
    ો
    1.82
    ා
    1.80
    s
    1.80
    Activations Density 0.097%

    No Known Activations