© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30107
    Prev
    Next
    INDEX
    Explanations

    damage to property

    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
    Negative Logits
    kiego
    -0.75
     lda
    -0.74
    щей
    -0.69
    hardt
    -0.69
    ilang
    -0.69
     incentiv
    -0.69
    vier
    -0.69
    outi
    -0.68
    lang
    -0.68
    oor
    -0.67
    POSITIVE LOGITS
     property
    5.94
    property
    4.59
     Property
    4.22
    Property
    4.16
     PROPERTY
    3.97
     properties
    3.63
    PROPERTY
    3.42
     propiedad
    3.02
    properties
    2.73
     propriété
    2.72
    Activations Density 0.036%

    No Known Activations