© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1705
    Prev
    Next
    INDEX
    Explanations

    python f-string formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azed
    1.51
    º
    1.48
    o
    1.44
    a
    1.39
    Richt
    1.35
    aner
    1.34
    هره
    1.31
    (-
    1.29
    oC
    1.28
    förm
    1.28
    POSITIVE LOGITS
    replaceAll
    1.42
    StringBuffer
    1.25
    哽
    1.22
    бов
    1.20
    removeChild
    1.16
    )=>
    1.14
     =>
    1.13
     essencial
    1.11
    emaakt
    1.10
     Besar
    1.09
    Activations Density 0.039%

    No Known Activations