© 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. 209611
    Prev
    Next
    INDEX
    Explanations

    already difficult

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

    food items, locations, or states

    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
     চী
    0.48
    욌
    0.47
    gra
    0.46
     rarer
    0.45
    软
    0.45
    谆
    0.44
     강
    0.43
     fluttering
    0.43
    卓
    0.43
     gra
    0.42
    POSITIVE LOGITS
     بعد
    0.48
     الابتدائي
    0.48
     ازاي
    0.47
    False
    0.47
     wakati
    0.46
     Amended
    0.44
    FALSE
    0.44
    桷
    0.44
     False
    0.43
    ACTIVE
    0.43
    Activations Density 0.001%

    No Known Activations