© 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. 233043
    Prev
    Next
    INDEX
    Explanations

    lists all products

    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
    ed
    0.55
    natal
    0.52
     Sinh
    0.51
    l
    0.51
     Tatha
    0.50
     Leopard
    0.48
     Lola
    0.47
    t
    0.47
     Investing
    0.47
    wealth
    0.47
    POSITIVE LOGITS
    ども
    0.47
    okinetic
    0.46
    طيكم
    0.45
    валі
    0.45
    Brazilian
    0.43
    ધન
    0.43
    গে
    0.43
    ಲೆಯ
    0.42
    ίου
    0.42
     fournir
    0.42
    Activations Density 0.001%

    No Known Activations