© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 22568
    Prev
    Next
    INDEX
    Explanations

    basis

    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_all/layer_41_width_262k_l0_big
    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
    綪
    0.40
     pewter
    0.39
    缝
    0.39
    Thể
    0.38
    括号
    0.38
    舜
    0.38
    烩
    0.38
    ুগ
    0.37
     kaw
    0.37
    垨
    0.37
    POSITIVE LOGITS
     basis
    1.14
     Basis
    1.10
    basis
    1.07
    Basis
    1.05
     orthonormal
    0.88
     BASIS
    0.87
     orthogonal
    0.82
     bases
    0.78
     linearly
    0.76
     Bases
    0.73
    Activations Density 0.004%

    No Known Activations