© 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. 11493
    Prev
    Next
    INDEX
    Explanations

    common and following words

    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
    فته
    2.45
    awatan
    2.31
    फारिश
    2.28
    刬
    2.26
    饬
    2.12
    ્ષ
    2.10
    ષા
    2.07
     العربية
    2.06
    arnas
    2.05
     bilan
    2.04
    POSITIVE LOGITS
    bodied
    2.12
    ———
    1.89
    u
    1.88
     punishable
    1.88
    occu
    1.85
    廨
    1.85
    𝔬
    1.81
    iyet
    1.81
    ————
    1.78
     tenement
    1.77
    Activations Density 0.116%

    No Known Activations