© 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. 27325
    Prev
    Next
    INDEX
    Explanations

    perpendicular and orthogonal geometry

    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
     小型
    0.45
    ꔰ
    0.44
     közé
    0.44
     ው
    0.43
    蟋
    0.41
    slideDuplicate
    0.40
     decays
    0.40
     AGA
    0.40
    はお
    0.39
     Inaug
    0.39
    POSITIVE LOGITS
     perpendicular
    0.77
     perpendicularly
    0.70
     perpend
    0.64
     orthogonal
    0.63
    ⊥
    0.57
     orthogonality
    0.52
    orthogonal
    0.52
     orthogon
    0.50
    perp
    0.50
     intersect
    0.48
    Activations Density 0.032%

    No Known Activations