© 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. 2635
    Prev
    Next
    INDEX
    Explanations

    the code, function, service, script, data, application

    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
    :
    0.67
    ://
    0.54
    ;
    0.52
    of
    0.44
     łat
    0.44
    :.
    0.43
    The
    0.42
     moyens
    0.42
     vzd
    0.42
     :
    0.41
    POSITIVE LOGITS
     dataset
    2.98
     betreff
    2.92
     jeweiligen
    2.87
    แต่ละ
    2.72
     jeweil
    2.67
    riera
    2.66
    合物
    2.64
    éments
    2.63
    プログラム
    2.63
     programme
    2.62
    Activations Density 0.892%

    No Known Activations