© 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. 107563
    Prev
    Next
    INDEX
    Explanations

    destroying or deleting

    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
    pton
    -0.79
     سا
    -0.75
    螫
    -0.73
     Tä
    -0.69
    ลิ
    -0.68
     правый
    -0.68
     Deacon
    -0.67
    ту
    -0.67
    preloader
    -0.67
    orté
    -0.66
    POSITIVE LOGITS
     destroy
    3.75
     Destroy
    3.70
    Destroy
    3.69
     destroyed
    3.38
    destroy
    3.33
     destruction
    3.31
     destroys
    2.89
     destroying
    2.78
     Destruction
    2.77
    DESTROY
    2.58
    Activations Density 0.037%

    No Known Activations