© 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. 5470
    Prev
    Next
    INDEX
    Explanations

    functional programming object programming

    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
    looms
    1.64
     Durable
    1.56
     ricev
    1.54
    ENCED
    1.53
     mientras
    1.53
     például
    1.52
    ҽ
    1.49
    鹊
    1.48
     terwijl
    1.46
    туа
    1.44
    POSITIVE LOGITS
     degrees
    0.90
    ленное
    0.80
    ∗</
    0.80
    iacute
    0.79
    Href
    0.79
     malice
    0.77
    ▿
    0.77
     hate
    0.76
     sentenced
    0.76
    ικής
    0.76
    Activations Density 0.038%

    No Known Activations