© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9065
    Prev
    Next
    INDEX
    Explanations

    COPPA

    np_acts-logits-general · gemini-2.5-flash-lite

    design of experiments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
    𒅌
    0.38
    and
    0.34
     McKin
    0.34
     Messrs
    0.33
    ्यारह
    0.33
    那位
    0.32
    지로
    0.31
    ස්
    0.31
    oces
    0.31
    자와
    0.31
    POSITIVE LOGITS
     này
    0.46
     to
    0.44
     से
    0.44
    <0xE6>
    0.43
     को
    0.42
    も
    0.42
    жуть
    0.42
    את
    0.41
     ущер
    0.41
     ਇਕ
    0.41
    Activations Density 2.766%

    No Known Activations