© 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. 86012
    Prev
    Next
    INDEX
    Explanations

    Ferrari

    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
     Welsh
    0.41
    鹽
    0.41
    ীকার
    0.39
    ARP
    0.38
     ARP
    0.38
    чку
    0.37
     महाप
    0.37
    覺
    0.37
    பால்
    0.37
    觉
    0.37
    POSITIVE LOGITS
     Ferrari
    1.37
    Ferrari
    1.30
     Ferr
    1.19
     ferr
    1.13
    Ferr
    1.12
     ferritin
    0.88
     ferrite
    0.86
     Ferris
    0.79
     SF
    0.73
     Fior
    0.73
    Activations Density 0.004%

    No Known Activations