© 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. 84510
    Prev
    Next
    INDEX
    Explanations

    business services and products

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

    fundamentally change, metrics, interacted, hidden

    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
     gjør
    0.50
     hacemos
    0.48
    𝘬
    0.47
    ίνουν
    0.46
     voltaje
    0.44
    ają
    0.43
    ặt
    0.43
     buku
    0.43
     marcó
    0.43
     gjøre
    0.42
    POSITIVE LOGITS
    Ply
    0.49
    s
    0.47
     зміни
    0.46
    ς
    0.46
     knives
    0.45
    的使用
    0.45
    Assured
    0.45
    Relatives
    0.43
     الخلف
    0.43
     orient
    0.43
    Activations Density 0.000%

    No Known Activations