© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107855
    Prev
    Next
    INDEX
    Explanations

    pressure and power

    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
    ^_^
    -0.87
    厕
    -0.75
    emoc
    -0.73
    ⅱ
    -0.73
    runOnUiThread
    -0.73
    кожа
    -0.71
     Bastion
    -0.71
    热血
    -0.70
    Salon
    -0.69
     ")");
    -0.68
    POSITIVE LOGITS
     pressure
    3.17
     power
    2.92
     Pressure
    2.66
    Pressure
    2.59
    pressure
    2.58
     PRESSURE
    2.20
    power
    2.17
     Power
    2.11
    Power
    2.11
     pressures
    1.88
    Activations Density 0.028%

    No Known Activations