© 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. 2617
    Prev
    Next
    INDEX
    Explanations

    programming constructs and numbers

    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
     Carol
    1.95
     NOR
    1.93
     Tsche
    1.91
     Han
    1.91
     Rast
    1.90
    interpol
    1.88
    빵
    1.84
     Primer
    1.83
    Orient
    1.83
     neur
    1.83
    POSITIVE LOGITS
    0
    1.80
    5
    1.57
    4
    1.49
    9
    1.46
    7
    1.44
    8
    1.43
    6
    1.43
    3
    1.41
    .
    1.35
    2
    1.33
    Activations Density 0.006%

    No Known Activations