© 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. 609
    Prev
    Next
    INDEX
    Explanations

    ultimately, choose, if

    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
     …………
    0.87
    …..
    0.87
     ……………………
    0.86
    :-)
    0.85
    ………..
    0.85
    .…
    0.85
    ……….
    0.83
    ….
    0.83
    .**
    0.83
    .—
    0.83
    POSITIVE LOGITS
    Therefore
    1.70
     Therefore
    1.67
     которое
    1.61
     However
    1.61
    However
    1.59
     которая
    1.57
    When
    1.56
    If
    1.56
     When
    1.55
    所以
    1.54
    Activations Density 0.944%

    No Known Activations