© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15944
    Prev
    Next
    INDEX
    Explanations

    since days of the week

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

    location identifiers

    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_31_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
    Mga
    0.37
     mga
    0.34
    G
    0.33
     The
    0.32
    </th>
    0.32
     Mga
    0.31
     French
    0.31
    <strong>
    0.30
    The
    0.30
     Santa
    0.30
    POSITIVE LOGITS
    reflectionCamera
    0.32
     vudd
    0.31
     quadrature
    0.30
    myCollision
    0.30
    ುವುದ
    0.29
     변화
    0.29
    坵
    0.29
    🤒
    0.29
    $\--
    0.28
     quadrupole
    0.28
    Activations Density 0.003%

    No Known Activations