© 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. 40-GEMMASCOPE-2-RES-262K
    7. 22987
    Prev
    Next
    INDEX
    Explanations

    background scripts and registry

    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_40_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
    々な
    0.37
     diffusive
    0.35
    вании
    0.34
    愚
    0.34
    Apollo
    0.33
    qid
    0.33
    irc
    0.33
    uix
    0.33
    east
    0.32
    AGUE
    0.32
    POSITIVE LOGITS
     Hostel
    0.42
     marshm
    0.40
     hostels
    0.40
     регистра
    0.38
     fortunately
    0.38
     Meadow
    0.38
     रजिस्टर
    0.37
    婊
    0.37
     aisles
    0.37
     Behind
    0.36
    Activations Density 0.001%

    No Known Activations