© 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. 40505
    Prev
    Next
    INDEX
    Explanations

    wave crests

    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
     Blackpool
    0.50
    㴡
    0.48
    لها
    0.45
     horticultural
    0.45
    •
    0.44
     ज्योग्राफी
    0.44
     perspectiva
    0.44
    冏
    0.42
    혔
    0.42
     Baran
    0.42
    POSITIVE LOGITS
     is
    0.56
    ä
    0.54
    wa
    0.51
    il
    0.50
     minutes
    0.48
     provides
    0.47
     are
    0.46
    az
    0.45
     released
    0.45
     ensures
    0.45
    Activations Density 0.002%

    No Known Activations