© 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. 62879
    Prev
    Next
    INDEX
    Explanations

    be considered or treated

    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
     not
    -1.09
     already
    -0.92
     intricacies
    -0.91
     ביט
    -0.91
    ()]
    -0.91
    家を
    -0.87
    ograft
    -0.87
    quelize
    -0.86
    创建时间
    -0.86
     there
    -0.85
    POSITIVE LOGITS
     treated
    1.05
     regarded
    1.05
     ogranic
    1.00
     considered
    0.99
     considéré
    0.98
    considered
    0.97
     subject
    0.96
     considerados
    0.95
     deemed
    0.95
     Considered
    0.93
    Activations Density 0.019%

    No Known Activations