© 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. 116207
    Prev
    Next
    INDEX
    Explanations

    game symbol

    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
    reuung
    -0.90
     promessa
    -0.86
    idalgo
    -0.84
    PutPixel
    -0.83
    temuan
    -0.82
    žití
    -0.81
    listdir
    -0.80
     MANT
    -0.79
     boneca
    -0.78
    ******/
    -0.77
    POSITIVE LOGITS
     property
    1.41
     properties
    1.32
    getProperties
    1.22
     Properties
    1.11
     hotels
    1.09
     Property
    1.09
     player
    1.07
    property
    1.06
     Community
    1.04
    properties
    1.02
    Activations Density 0.003%

    No Known Activations