© 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. 53683
    Prev
    Next
    INDEX
    Explanations

    brands, guys, comfortable, correct, testimony, decide, ways

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

    examples using `feature` and `AI`

    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
    ικη
    0.51
     началь
    0.49
    на
    0.48
    f
    0.47
    க
    0.47
     Phyl
    0.47
     nincs
    0.46
     telle
    0.46
     uzyska
    0.46
     Pogis
    0.46
    POSITIVE LOGITS
    नीकरण
    0.47
    Saturday
    0.44
    测
    0.41
    cutaneous
    0.40
    IRM
    0.40
    LOS
    0.39
    Labor
    0.39
     बटा
    0.38
    geoLocation
    0.38
    Middleware
    0.38
    Activations Density 0.000%

    No Known Activations