© 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. 92848
    Prev
    Next
    INDEX
    Explanations

    errors or specific identifiers

    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
     pey
    -0.79
    urons
    -0.79
    Дополнитель
    -0.77
     turg
    -0.77
     conflu
    -0.76
    őtt
    -0.76
     gratefully
    -0.76
     prate
    -0.75
    CLOSURE
    -0.75
     pét
    -0.75
    POSITIVE LOGITS
     caller
    0.87
     nhi
    0.87
     insufficient
    0.86
     Insufficient
    0.84
     invalid
    0.82
     precisa
    0.80
     аниме
    0.79
    wanan
    0.79
     jūs
    0.79
     actualidad
    0.78
    Activations Density 0.001%

    No Known Activations