© 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. 197128
    Prev
    Next
    INDEX
    Explanations

    listings, stored, invested, donate, provider

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

    Reveal problems province noodles

    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
    Ա
    0.55
    LIVE
    0.54
    Microsoft
    0.51
    July
    0.49
    Address
    0.49
    Live
    0.48
    BOOL
    0.48
    以此
    0.47
    Excuse
    0.47
    Կ
    0.46
    POSITIVE LOGITS
     দায়িত্ব
    0.56
     embroidered
    0.54
     ван
    0.50
     дизайне
    0.50
    тивний
    0.49
     кон
    0.49
     вокруг
    0.48
     Embro
    0.48
     темпера
    0.47
     छापे
    0.47
    Activations Density 0.001%

    No Known Activations