© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14833
    Prev
    Next
    INDEX
    Explanations

    comparisons followed by clauses

    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_22/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
     from
    -1.48
    opposed
    -0.94
    샌
    -0.90
     aparcamiento
    -0.89
     ТА
    -0.86
     وليس
    -0.85
     alongside
    -0.85
     versus
    -0.85
     recomand
    -0.84
     Gegensatz
    -0.81
    POSITIVE LOGITS
     but
    1.13
     debido
    1.05
     they
    1.05
     때문에
    1.05
    更容易
    1.03
     difference
    1.03
    Closer
    0.98
    儚
    0.97
     because
    0.96
     differences
    0.94
    Activations Density 0.070%

    No Known Activations