© 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. 5657
    Prev
    Next
    INDEX
    Explanations

    rest for 5-10 minutes

    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
    outof
    1.83
    tzmann
    1.80
    tedir
    1.76
    año
    1.75
    谎
    1.74
    fordert
    1.72
    のではなく
    1.70
    pura
    1.62
    galactos
    1.61
     درون
    1.58
    POSITIVE LOGITS
     леп
    1.54
     Towers
    1.49
     tranh
    1.47
    <0xD2>
    1.47
     Bridges
    1.46
     Peaks
    1.44
    shard
    1.41
     Deleg
    1.41
     ابي
    1.40
     Documentation
    1.40
    Activations Density 0.015%

    No Known Activations