© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78678
    Prev
    Next
    INDEX
    Explanations

    using existing hardware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     analysts
    0.46
    Ray
    0.45
    6
    0.45
     analysis
    0.45
    Police
    0.45
    analysis
    0.44
    Delhi
    0.44
    class
    0.43
    pressure
    0.43
     in
    0.42
    POSITIVE LOGITS
     然而
    0.53
     χρησιμοποι
    0.52
     adhipp
    0.49
     È
    0.47
     моего
    0.45
     Alguns
    0.45
     Algunos
    0.45
     சகோ
    0.45
     полити
    0.44
     もう
    0.44
    Activations Density 0.002%

    No Known Activations