© 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. 12-GEMMASCOPE-2-RES-16K
    7. 5226
    Prev
    Next
    INDEX
    Explanations

    states or 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_12_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
     in
    3.52
    in
    2.90
    在
    2.61
    在其
    2.25
    在他的
    2.15
    In
    2.14
     on
    2.14
     In
    2.12
    i
    2.10
     dalam
    2.07
    POSITIVE LOGITS
     vitro
    2.40
     delectable
    2.23
    )").
    2.21
    พาะ
    2.21
     shrewd
    2.18
    📫
    2.07
     yummy
    2.05
    📪
    2.04
    ProjectGuid
    2.01
     yksi
    2.01
    Activations Density 0.107%

    No Known Activations