© 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. 1977
    Prev
    Next
    INDEX
    Explanations

    what comes next after these

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

    chorus labels

    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
     ensures
    0.49
     i
    0.49
     prevents
    0.47
     redis
    0.46
     re
    0.45
     u
    0.45
     dispose
    0.45
     trex
    0.44
     attrib
    0.44
     pach
    0.43
    POSITIVE LOGITS
     أبو
    0.50
    ។
    0.49
    ۔
    0.48
    lavery
    0.47
    cuando
    0.47
    church
    0.47
    duke
    0.47
     músicos
    0.45
     Христос
    0.45
    ciplinary
    0.45
    Activations Density 0.000%

    No Known Activations