© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98185
    Prev
    Next
    INDEX
    Explanations

    United States Court of Appeals

    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
     toes
    -1.22
     foot
    -1.22
    toes
    -1.13
     toe
    -1.07
    foot
    -1.06
    toe
    -1.00
    Foot
    -0.94
     Foot
    -0.90
     feet
    -0.89
     Looks
    -0.84
    POSITIVE LOGITS
                                   
    1.81
    1.30
    0.96
    0.86
     falsch
    0.86
     Presbyter
    0.78
    ฌ
    0.77
    crivez
    0.75
     rê
    0.74
     größe
    0.74
    Activations Density 0.019%

    No Known Activations