© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12503
    Prev
    Next
    INDEX
    Explanations

    let me know

    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_13_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
    estable
    1.01
    angwa
    0.95
    악
    0.94
    odne
    0.94
    est
    0.94
    男女
    0.93
    od
    0.92
    勅
    0.91
    or
    0.90
    si
    0.89
    POSITIVE LOGITS
     Deals
    1.39
     назад
    1.28
    ያስ
    1.26
     wówczas
    1.25
     Multipart
    1.23
     ㅁ
    1.21
     quinta
    1.20
     Technik
    1.20
     cạnh
    1.20
     आपका
    1.19
    Activations Density 0.114%

    No Known Activations