© 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. 21440
    Prev
    Next
    INDEX
    Explanations

    over time

    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
    kelly
    0.40
    Gad
    0.38
     Adams
    0.38
    ↵
    0.38
    Jim
    0.36
     Handbook
    0.36
     granted
    0.36
    ↵↵
    0.35
    iqué
    0.35
    né
    0.34
    POSITIVE LOGITS
     reliance
    0.54
     overcoming
    0.52
     overcame
    0.47
     overturning
    0.46
     രണ്ട്
    0.46
     రెండు
    0.46
    克服
    0.45
     преодо
    0.45
     overarching
    0.44
     overgrown
    0.44
    Activations Density 0.003%

    No Known Activations