© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4441
    Prev
    Next
    INDEX
    Explanations

    score changes

    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
    <0xC2>
    1.25
    AG
    1.21
    Con
    1.17
    ‎
    1.14
     Via
    1.14
    NE
    1.12
     Op
    1.12
    〈
    1.11
     Pod
    1.11
    Cor
    1.09
    POSITIVE LOGITS
    oseconds
    2.49
    したいと思います
    2.45
     hesitate
    2.44
     busier
    2.43
    öglichkeiten
    2.41
     ceases
    2.41
    ipennis
    2.38
    iculty
    2.38
    ogeneities
    2.35
    iophor
    2.35
    Activations Density 1.555%

    No Known Activations