© 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. 3500
    Prev
    Next
    INDEX
    Explanations

    model initiating response

    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
    酮
    1.47
    ⓒ
    1.39
    şık
    1.29
    árez
    1.25
     outputFile
    1.25
    édez
    1.19
    وصل
    1.19
    兼用
    1.17
    讃
    1.17
    在一起
    1.15
    POSITIVE LOGITS
     облег
    1.18
     perplex
    1.14
     innoc
    1.09
    dre
    1.03
     guiding
    0.99
    Username
    0.99
     pust
    0.98
     victor
    0.98
     vieux
    0.97
    viously
    0.97
    Activations Density 0.120%

    No Known Activations