© 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. 40-GEMMASCOPE-2-RES-262K
    7. 36202
    Prev
    Next
    INDEX
    Explanations

    engine coolant and radiators

    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_40_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
     вз
    0.40
     diurnal
    0.38
     snapper
    0.38
     synaptic
    0.37
     ձ
    0.37
     biometric
    0.37
    iores
    0.37
    ariamente
    0.37
    렷
    0.36
     sab
    0.36
    POSITIVE LOGITS
     coolant
    1.09
     radiator
    1.04
     thermostat
    0.91
     radiators
    0.90
     thermostats
    0.81
    Water
    0.71
     cooling
    0.70
    散热
    0.70
    WATER
    0.66
     Cooling
    0.66
    Activations Density 0.005%

    No Known Activations