© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34633
    Prev
    Next
    INDEX
    Explanations

    movement and position changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Both
    -1.05
    ceptives
    -0.98
    Unlike
    -0.97
     hosszú
    -0.97
    すべての
    -0.95
     لكل
    -0.95
    这种
    -0.93
     móds
    -0.93
    ombies
    -0.92
    selbe
    -0.92
    POSITIVE LOGITS
     into
    1.31
     its
    1.24
    的位置
    1.15
     위치
    1.13
     position
    1.12
    の位置
    1.11
     to
    1.10
     away
    1.00
     the
    0.97
     junto
    0.96
    Activations Density 0.054%

    No Known Activations