© 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. 189715
    Prev
    Next
    INDEX
    Explanations

    horseback riding

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

    descriptive conditions and agents

    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
     density
    0.55
     stitches
    0.51
     rectangle
    0.50
     kites
    0.49
    :
    0.48
     horizontal
    0.48
     color
    0.47
     fish
    0.46
     power
    0.46
     histogram
    0.46
    POSITIVE LOGITS
    ່າຍ
    0.50
    ánto
    0.50
     keltiradi
    0.49
    좆
    0.49
    れて
    0.48
    പ്പം
    0.48
     ఇతర
    0.48
    ன்றும்
    0.48
     გამოი
    0.46
    ര്‍ട്ട്
    0.46
    Activations Density 0.002%

    No Known Activations