© 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. 223668
    Prev
    Next
    INDEX
    Explanations

    return flight

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

    parsing numbers and code constructs

    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
     সন্ধ্যায়
    0.50
     সভায়
    0.48
    橥
    0.47
     Protección
    0.46
    èvement
    0.46
    ಗ್ಗೆ
    0.46
     Após
    0.46
     ಗೆ
    0.46
     ಪ್ರಕರಣ
    0.46
     Núñez
    0.46
    POSITIVE LOGITS
    oly
    0.46
     paleo
    0.46
     enlisted
    0.43
    டுப
    0.43
     gott
    0.43
     spust
    0.42
    ט
    0.42
    ات
    0.42
    Japanese
    0.41
     pyl
    0.41
    Activations Density 0.000%

    No Known Activations