© 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. 34-GEMMASCOPE-RES-131K
    7. 65205
    Prev
    Next
    INDEX
    Explanations

    Ferris Wheel

    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
    Портал
    -0.82
     Tender
    -0.75
     entitlement
    -0.69
     Aze
    -0.69
    vers
    -0.68
     IBC
    -0.68
    Mental
    -0.67
    Relational
    -0.67
    bbq
    -0.66
    ಹ
    -0.66
    POSITIVE LOGITS
     Ferris
    2.84
     ferr
    2.48
     wheel
    2.38
     Wheel
    2.13
    wheel
    2.09
    Wheel
    1.94
    Ferr
    1.90
     WHEEL
    1.74
    WHEEL
    1.71
     wheels
    1.60
    Activations Density 0.026%

    No Known Activations