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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 12088
    Prev
    Next
    INDEX
    Explanations

    battery life

    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
    ビング
    -0.81
    textLabel
    -0.74
     куро
    -0.72
     Protestant
    -0.72
    neet
    -0.69
    Loves
    -0.69
    erencia
    -0.68
    paddingTop
    -0.68
    runken
    -0.68
    leukin
    -0.67
    POSITIVE LOGITS
     battery
    6.00
     batteries
    5.25
    battery
    4.31
    Battery
    4.16
     Battery
    4.16
     Batteries
    3.56
     BATTERY
    3.30
    バッテリー
    3.28
    BATTERY
    3.23
     batería
    3.16
    Activations Density 0.082%

    No Known Activations