© 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. 219402
    Prev
    Next
    INDEX
    Explanations

    tracker tk

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

    why and though

    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
    )=
    0.54
    favorites
    0.54
     август
    0.53
    feb
    0.50
    loans
    0.50
     भविष्यवाणी
    0.49
    8
    0.48
     बंध
    0.48
     प्रणाली
    0.48
     अच
    0.47
    POSITIVE LOGITS
     Univ
    0.47
    輟
    0.47
     Produits
    0.46
     quartier
    0.43
     senden
    0.43
    ား
    0.42
     تقدم
    0.41
     Cardiol
    0.41
     washer
    0.41
    ાસ
    0.41
    Activations Density 0.000%

    No Known Activations