© 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. 223145
    Prev
    Next
    INDEX
    Explanations

    coffee stains, novel begun, avoids explicit

    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
    虹
    0.43
     წარ
    0.42
    ेबल
    0.41
     गट
    0.41
     गटा
    0.41
    蒌
    0.41
    Amend
    0.40
    टका
    0.40
    檸
    0.40
    轵
    0.40
    POSITIVE LOGITS
     observed
    0.45
     observation
    0.43
     pe
    0.42
     zur
    0.40
    0.39
     base
    0.38
     PE
    0.37
     samoz
    0.37
     долго
    0.37
     bis
    0.36
    Activations Density 0.001%

    No Known Activations