© 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. 111755
    Prev
    Next
    INDEX
    Explanations

    a fully

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

    model introducing concepts

    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
     prerog
    0.52
    斟
    0.48
     figurines
    0.45
    hesion
    0.44
     किशन
    0.43
    RECTION
    0.43
     сидя
    0.42
    ೇಳ
    0.42
     божомол
    0.42
    ｶ
    0.42
    POSITIVE LOGITS
    SpringBoot
    0.50
     ausgezeichnet
    0.43
     Brexit
    0.43
    GeV
    0.43
     Escape
    0.43
     Commonwealth
    0.41
    ట్లో
    0.41
     escape
    0.41
     sanitized
    0.41
     pett
    0.41
    Activations Density 0.001%

    No Known Activations