© 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. 11129
    Prev
    Next
    INDEX
    Explanations

    acts as a

    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
    нду
    2.38
    н
    2.33
    ン
    2.25
    หน
    2.20
    n
    2.14
    нской
    2.13
    กล่าว
    2.06
    derdag
    2.06
    a
    2.04
    ss
    2.01
    POSITIVE LOGITS
     백
    1.94
    렛
    1.88
     accrue
    1.86
     suất
    1.86
     contribute
    1.83
    𝐊
    1.82
    백
    1.82
    θν
    1.80
    աջ
    1.77
     রহিম
    1.76
    Activations Density 0.083%

    No Known Activations