© 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. 33792
    Prev
    Next
    INDEX
    Explanations

    riding or ride related words

    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
     incur
    0.42
     சு
    0.40
    ettamente
    0.36
    
    0.36
     μά
    0.36
    वृत्ति
    0.35
    👁
    0.35
    ⏪
    0.35
     الكون
    0.34
    eningrad
    0.33
    POSITIVE LOGITS
     riding
    1.70
     Riding
    1.55
     ride
    1.36
     rides
    1.31
    riding
    1.31
     Ride
    1.27
     rode
    1.27
    に乗
    1.18
    Ride
    1.18
    乗
    1.18
    Activations Density 0.001%

    No Known Activations