© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91587
    Prev
    Next
    INDEX
    Explanations

    dermatologist tested, ships returning

    np_acts-logits-general · gemini-2.5-flash-lite

    what kind of results to expect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
       
    0.46
    Dec
    0.45
    ruled
    0.41
    ers
    0.41
    arm
    0.41
    nick
    0.39
     commissioner
    0.38
    ’
    0.38
    halation
    0.37
    compatible
    0.37
    POSITIVE LOGITS
    𝓾
    0.54
     дис
    0.53
     وي
    0.53
     intraven
    0.50
     vede
    0.50
     Séb
    0.49
     nepř
    0.49
    ግኘት
    0.49
    макра
    0.49
     intuit
    0.47
    Activations Density 0.001%

    No Known Activations