© 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. 31-GEMMASCOPE-2-RES-262K
    7. 111071
    Prev
    Next
    INDEX
    Explanations

    python class definitions

    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_31_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
    >≤</
    0.51
     bathtub
    0.50
     Pó
    0.47
     Prey
    0.47
     computeEncoder
    0.46
     dependability
    0.46
     =-
    0.46
     勺
    0.45
     previewBuilder
    0.45
     objectMapper
    0.44
    POSITIVE LOGITS
    Clean
    0.54
    crafted
    0.52
    You
    0.51
    ographed
    0.49
    Andreas
    0.48
    read
    0.47
    Share
    0.46
    of
    0.45
    Questions
    0.45
    kan
    0.45
    Activations Density 0.003%

    No Known Activations