© 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. 27325
    Prev
    Next
    INDEX
    Explanations

    perpendicular and orthogonal

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

    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-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
     AGA
    0.46
     divul
    0.44
     razum
    0.44
     ç
    0.42
     közé
    0.41
    棫
    0.41
     güz
    0.41
     vivere
    0.40
     Ouais
    0.40
     kontinuier
    0.40
    POSITIVE LOGITS
     perpendicularly
    0.71
     perpendicular
    0.68
     orthogonal
    0.68
    ⊥
    0.63
     perpend
    0.63
    orthogonal
    0.61
     orthogonality
    0.61
     orthogon
    0.59
    perp
    0.52
     intersects
    0.49
    Activations Density 0.009%

    No Known Activations