© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 221346
    Prev
    Next
    INDEX
    Explanations

    water, calculations, expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🧉
    0.40
     Prospect
    0.39
    /).
    0.38
    ∂</
    0.37
    繫
    0.37
    /');
    0.37
    Prospect
    0.36
     parcels
    0.35
     Stationery
    0.35
    芜
    0.35
    POSITIVE LOGITS
     वोल्ट
    0.41
    führ
    0.40
     adenosine
    0.39
     therapeutic
    0.38
     नाइट्र
    0.38
    ethane
    0.38
     چاندی
    0.38
    nity
    0.37
     আওয়ামী
    0.37
    ໃຫ້
    0.37
    Activations Density 0.003%

    No Known Activations