© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3643
    Prev
    Next
    INDEX
    Explanations

    compile code

    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
    ."},
    1.06
    hesi
    1.04
    osus
    1.02
    werp
    0.99
    elsen
    0.98
    quinone
    0.96
    γή
    0.93
    ën
    0.93
    ineux
    0.92
    elson
    0.92
    POSITIVE LOGITS
    کر
    1.37
    <unused1728>
    1.36
     regress
    1.35
    fool
    1.34
     سلام
    1.32
    Sail
    1.31
     alman
    1.30
    참
    1.29
    gruntled
    1.29
    羡慕
    1.28
    Activations Density 0.021%

    No Known Activations