© 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. 2717
    Prev
    Next
    INDEX
    Explanations

    mathematical properties and characteristics

    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
     considér
    -0.87
    に関しては
    -0.86
    ffy
    -0.85
    offsetY
    -0.85
     gagner
    -0.84
    edy
    -0.82
    unnitel
    -0.81
     elementy
    -0.81
     MICHAEL
    -0.81
    яв
    -0.81
    POSITIVE LOGITS
     property
    1.18
     characteristics
    1.18
    PROPERTY
    1.13
     properties
    1.02
    During
    0.99
     Property
    0.98
    Property
    0.94
     属性
    0.91
     cheerful
    0.91
     associated
    0.90
    Activations Density 0.150%

    No Known Activations