© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9262
    Prev
    Next
    INDEX
    Explanations

    transmission types and gearboxes

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

    gear and transmission

    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_40_width_16k_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
    辏
    0.45
     asesinato
    0.42
     डोर
    0.40
     vasomotor
    0.40
     anticor
    0.39
    platinum
    0.39
     নেতাদের
    0.39
     અધ
    0.39
    颊
    0.38
     platinum
    0.38
    POSITIVE LOGITS
     transmissions
    1.49
     transmission
    1.44
     gearbox
    1.38
    Transmission
    1.37
    transmission
    1.34
     Transmission
    1.33
     gear
    1.27
     Gear
    1.23
     transmissão
    1.21
     transmisión
    1.20
    Activations Density 0.138%

    No Known Activations