© 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. 2923
    Prev
    Next
    INDEX
    Explanations

    Transmission Control Protocol

    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
    𝗿
    2.84
    𝘀
    2.83
    𝗹
    2.70
    𝗴
    2.64
    𝘃
    2.64
    壹章
    2.62
    𝑬
    2.60
    𝗷
    2.58
    𝗻
    2.57
    𝗲
    2.56
    POSITIVE LOGITS
    an
    2.97
    s
    2.71
    a
    2.58
    isieren
    2.55
    al
    2.49
    ي
    2.43
    aný
    2.42
    ০
    2.40
    anah
    2.26
    isier
    2.17
    Activations Density 0.053%

    No Known Activations