© 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. 98379
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     such
    -1.27
    Composición
    -0.91
     такі
    -0.86
     accelerating
    -0.82
     afirmar
    -0.81
    gingen
    -0.79
    ња
    -0.77
    Artículos
    -0.77
     таких
    -0.75
     еле
    -0.73
    POSITIVE LOGITS
     卓
    0.98
    AddNew
    0.97
    তথ্য
    0.92
     assortment
    0.91
     Advertisement
    0.88
    ١
    0.88
    eció
    0.88
    ]]>
    0.87
    }}^{\
    0.84
     showcased
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.