© 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. 11457
    Prev
    Next
    INDEX
    Explanations

    tv shows

    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
    𝐥
    2.96
    𝐤
    2.77
    𝐢
    2.67
    𝐠
    2.58
    𝐬
    2.48
     counters
    2.39
    mal
    2.34
    </h2>
    2.30
    )|$(
    2.28
    ist
    2.22
    POSITIVE LOGITS
    DEFGHIJKLMNOP
    3.39
     تعالى
    3.03
    اتے
    2.93
    ઈ
    2.89
     تعالی
    2.86
    खास्त
    2.82
    sourceFolder
    2.81
    ுள்ளார்
    2.78
    تری
    2.77
     PDPN
    2.73
    Activations Density 0.012%

    No Known Activations