© 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. 31-GEMMASCOPE-2-RES-262K
    7. 199853
    Prev
    Next
    INDEX
    Explanations

    phrasal collocations and sequences

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

    statistical analysis or bourbon

    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_262k_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
     árboles
    0.62
     Flügel
    0.52
     módulos
    0.51
    ленность
    0.50
    绦
    0.50
     Galicia
    0.49
    胁
    0.48
     Liss
    0.48
     Vivi
    0.48
     Grün
    0.48
    POSITIVE LOGITS
     ></
    0.54
    ical
    0.52
    <unused60>
    0.50
    <unused63>
    0.48
    court
    0.48
    0.46
    text
    0.46
    0.45
    $&
    0.44
    <unused61>
    0.44
    Activations Density 0.000%

    No Known Activations