© 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. 106638
    Prev
    Next
    INDEX
    Explanations

    infinite scroll and loops

    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
     online
    -1.02
    Ac
    -0.94
    online
    -0.91
     trois
    -0.91
    インターネット
    -0.90
    relatively
    -0.86
     hefty
    -0.85
    Iso
    -0.84
     drei
    -0.83
    shat
    -0.83
    POSITIVE LOGITS
    ♾
    1.33
     Endless
    1.10
     Infinite
    1.10
     ∞
    1.09
    Endless
    1.09
     endless
    1.06
    infinite
    1.05
     loop
    1.04
     infinite
    1.02
     possibilities
    1.01
    Activations Density 0.019%

    No Known Activations