© 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. 31072
    Prev
    Next
    INDEX
    Explanations

    mining, exploration, projects

    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
     specialized
    -0.83
     like
    -0.79
     pertaining
    -0.76
     <",
    -0.70
    Before
    -0.70
    了呢
    -0.69
    Since
    -0.69
     passenden
    -0.68
    ENTS
    -0.68
     vicente
    -0.68
    POSITIVE LOGITS
     property
    1.49
     Property
    1.43
    property
    1.32
     deposit
    1.27
     properties
    1.24
     PROPERTY
    1.19
     project
    1.16
     propriété
    1.14
     propiedades
    1.13
    Property
    1.13
    Activations Density 0.012%

    No Known Activations