© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2058
    Prev
    Next
    INDEX
    Explanations

    capitalized letters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    حد
    1.68
     neu
    1.68
     stri
    1.67
     kom
    1.65
     vien
    1.64
     высоко
    1.63
     portug
    1.63
     免
    1.62
     bril
    1.62
     све
    1.61
    POSITIVE LOGITS
     C
    2.22
     L
    2.18
     E
    2.17
     S
    2.16
     D
    2.14
     T
    2.13
     M
    2.10
     R
    2.09
     P
    2.09
     N
    2.01
    Activations Density 0.703%

    No Known Activations