© 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. 63
    Prev
    Next
    INDEX
    Explanations

    appears to be suitable

    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
     مۇ
    3.49
    ﺰ
    3.43
    Ց
    3.40
    연
    3.40
     އ
    3.39
     Toute
    3.39
     ډ
    3.39
    ஔ
    3.38
     请
    3.37
    AdType
    3.35
    POSITIVE LOGITS
    喙
    -0.01
    惕
    -0.21
    搓
    -0.28
    tell
    -0.29
    さに
    -0.31
    下が
    -0.31
     ",")
    -0.34
     insuficiente
    -0.35
    knię
    -0.40
    そうな
    -0.41
    Activations Density 0.424%

    No Known Activations