© 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. 47788
    Prev
    Next
    INDEX
    Explanations

    final words and endings

    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
     primero
    -1.20
     hablando
    -1.12
     primeiro
    -1.05
     suced
    -1.05
     siguiendo
    -1.03
     çeşitli
    -1.03
    ването
    -1.00
     nuevo
    -1.00
     first
    -0.98
     знали
    -0.97
    POSITIVE LOGITS
    ising
    1.51
    izing
    1.41
    izers
    1.41
    Final
    1.30
    ization
    1.27
     Final
    1.27
     FINAL
    1.18
     touches
    1.17
    isers
    1.15
     destination
    1.07
    Activations Density 0.020%

    No Known Activations