© 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-65K
    7. 20020
    Prev
    Next
    INDEX
    Explanations

    slope and graph relationships

    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_65k_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
    cosis
    0.46
     chitin
    0.43
     quorum
    0.42
     षटके
    0.41
    stung
    0.40
     jurors
    0.40
    뷁
    0.39
     polymerized
    0.39
     cytotoxicity
    0.39
     macer
    0.39
    POSITIVE LOGITS
    Slope
    0.87
     slope
    0.82
     Slope
    0.81
    slope
    0.75
     slopes
    0.68
    Regression
    0.58
    Curve
    0.57
    Graph
    0.55
     graphing
    0.54
     斜
    0.52
    Activations Density 0.185%

    No Known Activations