© 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. 16947
    Prev
    Next
    INDEX
    Explanations

    orientation or direction

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

    direction and orientation

    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
    د
    1.01
     in
    0.83
     or
    0.71
    {
    0.71
    I
    0.69
    д
    0.68
    ח
    0.68
    AA
    0.64
    ים
    0.62
    ح
    0.62
    POSITIVE LOGITS
    向き
    0.88
    方向
    0.87
     hướng
    0.86
     Direction
    0.86
    に向け
    0.86
    direction
    0.85
     yön
    0.82
    方向に
    0.82
    Direction
    0.81
     direction
    0.80
    Activations Density 0.025%

    No Known Activations