© 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. 117182
    Prev
    Next
    INDEX
    Explanations

    value and increases

    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
     groote
    -1.00
     begon
    -0.96
     klein
    -0.94
     brune
    -0.94
     vitale
    -0.92
     heer
    -0.91
    Чыганаклар
    -0.89
     witte
    -0.88
    гаре
    -0.87
     poë
    -0.86
    POSITIVE LOGITS
     value
    2.58
     appreciation
    2.41
     resale
    2.09
     values
    2.02
     appreciating
    1.91
     appreciates
    1.75
     increase
    1.75
     appreciate
    1.74
     Appreciation
    1.66
     increases
    1.57
    Activations Density 0.021%

    No Known Activations