© 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. 40-GEMMASCOPE-2-RES-262K
    7. 470
    Prev
    Next
    INDEX
    Explanations

    numbers and costs

    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
     HUR
    0.18
     הש
    0.18
    及
    0.18
     approximate
    0.18
     incentiv
    0.17
    浑
    0.17
    няў
    0.17
     in
    0.17
     מח
    0.17
     untapped
    0.17
    POSITIVE LOGITS
    0
    0.29
    )));
    0.22
    two
    0.22
    five
    0.21
    4
    0.21
    3
    0.20
    json
    0.20
    yes
    0.20
    true
    0.19
    os
    0.19
    Activations Density 0.207%

    No Known Activations