© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7632
    Prev
    Next
    INDEX
    Explanations

    motor vehicles

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

    motor vehicles or control

    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_53_width_65k_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
     सोचने
    0.40
    mortar
    0.39
     THINK
    0.38
    etel
    0.38
    ᒪ
    0.38
    aré
    0.37
    дово
    0.37
    utis
    0.37
    蒟
    0.37
    Somebody
    0.37
    POSITIVE LOGITS
    bikes
    0.75
     scooter
    0.70
     motor
    0.66
    ized
    0.64
     neuron
    0.63
    bike
    0.62
    vehicle
    0.61
    neuron
    0.61
    ola
    0.60
    iklet
    0.60
    Activations Density 0.019%

    No Known Activations