© 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. 53-GEMMASCOPE-2-RES-262K
    7. 63042
    Prev
    Next
    INDEX
    Explanations

    scooters and Honda models

    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/layer_53_width_262k_l0_medium
    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
     camels
    0.39
    缎
    0.39
    pans
    0.37
     മുഹമ്മ
    0.36
     horses
    0.36
    ிர்
    0.35
    Twin
    0.35
    খর
    0.35
    荆
    0.35
     prosthetic
    0.35
    POSITIVE LOGITS
     scooter
    1.16
     scooters
    1.05
     Sco
    1.02
     scoot
    0.98
     Scooter
    0.98
    Sco
    0.96
     Vespa
    0.95
     स्कूटर
    0.86
     Pi
    0.79
     ves
    0.77
    Activations Density 0.003%

    No Known Activations