© 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. 6626
    Prev
    Next
    INDEX
    Explanations

    comma and

    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
    볕
    1.54
     amante
    1.53
    姿
    1.51
    情况下
    1.51
    žete
    1.49
    dym
    1.48
    但是在
    1.47
    慟
    1.45
    外的
    1.45
     unattended
    1.44
    POSITIVE LOGITS
     publishing
    2.12
    collabor
    2.06
     collaborating
    1.94
     producing
    1.93
     Ponte
    1.90
     reopening
    1.89
    developing
    1.87
     developing
    1.83
    publishing
    1.82
     revisiting
    1.82
    Activations Density 0.000%

    No Known Activations