© 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. 118834
    Prev
    Next
    INDEX
    Explanations

    e4

    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
    ный
    0.41
    fund
    0.38
    department
    0.38
     bese
    0.38
     funded
    0.38
     اکت
    0.37
    enged
    0.37
    及
    0.36
    do
    0.36
     sog
    0.35
    POSITIVE LOGITS
    雰囲気
    0.41
    unya
    0.40
     presently
    0.39
    闱
    0.39
     हथ
    0.38
     Atmosphere
    0.38
     Hickory
    0.38
     pabc
    0.38
     Presently
    0.37
     Thieves
    0.37
    Activations Density 0.004%

    No Known Activations