© 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. 12-GEMMASCOPE-2-RES-16K
    7. 4062
    Prev
    Next
    INDEX
    Explanations

    introduces results or next steps

    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
    ↵
    2.95
    .
    2.89
    ↵↵
    2.74
    :
    2.48
    ↵↵↵
    2.15
    !
    1.95
    '
    1.89
    ↵↵↵↵
    1.77
    <eos>
    1.76
    。
    1.75
    POSITIVE LOGITS
     Whenever
    2.61
     Furthermore
    2.54
     insofar
    2.49
     Though
    2.47
     Depending
    2.44
     Additionally
    2.43
     Likewise
    2.37
     Moreover
    2.32
     inasmuch
    2.31
     Consequently
    2.29
    Activations Density 0.068%

    No Known Activations