© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 27893
    Prev
    Next
    INDEX
    Explanations

    regex explanation

    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
     संरक्षण
    0.48
    理工
    0.48
    㧕
    0.46
     खेले
    0.45
    おか
    0.45
     상관
    0.45
    보고
    0.45
    拁
    0.44
    ंसाठी
    0.44
    頂き
    0.43
    POSITIVE LOGITS
    Platform
    0.41
     transition
    0.39
    Houses
    0.38
     FirebaseAuth
    0.37
     houses
    0.36
    Desktop
    0.36
     salaried
    0.36
     branched
    0.35
     createUser
    0.35
     sought
    0.34
    Activations Density 0.004%

    No Known Activations