© 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. 31152
    Prev
    Next
    INDEX
    Explanations

    motor sport and cars

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

    motorsport races

    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
     ভাইরাল
    0.52
     infantil
    0.51
     sozialen
    0.50
     塩
    0.49
    憂
    0.49
    🚶
    0.49
    🦶
    0.49
    習慣
    0.48
     কবিতার
    0.48
     уголов
    0.48
    POSITIVE LOGITS
     motorsport
    1.41
     Motorsport
    1.27
     racing
    1.24
     Racing
    1.19
     racers
    1.18
    racing
    1.10
     Motorsports
    1.07
     racer
    1.06
     FIA
    1.03
    Racing
    1.01
    Activations Density 0.163%

    No Known Activations