© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91904
    Prev
    Next
    INDEX
    Explanations

    air conditioning and climate control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ₛ
    -0.87
     söyl
    -0.76
     estético
    -0.75
    дила
    -0.73
    сці
    -0.70
     officiels
    -0.70
    odenal
    -0.68
     atenta
    -0.68
    یمت
    -0.68
     cyanide
    -0.67
    POSITIVE LOGITS
     AC
    2.61
     air
    2.56
    空调
    2.25
     конди
    2.22
     HVAC
    2.17
    エアコン
    1.98
    AC
    1.86
     Air
    1.75
     climate
    1.73
     cooling
    1.70
    Activations Density 0.029%

    No Known Activations