© 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. 6236
    Prev
    Next
    INDEX
    Explanations

    athletes earning or winning championships

    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
     해도
    1.41
     gewähr
    1.33
    팡
    1.30
    释
    1.29
    ัพท์
    1.29
     enfe
    1.28
    UINT
    1.26
    ostrat
    1.26
     Yamamoto
    1.24
    vable
    1.23
    POSITIVE LOGITS
    児
    1.19
    urken
    1.17
    积累
    1.12
     یورو
    1.11
     българ
    1.10
    urk
    1.10
    々は
    1.10
    HOB
    1.09
    abody
    1.07
    rami
    1.06
    Activations Density 0.060%

    No Known Activations