© 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. 10-GEMMASCOPE-RES-131K
    7. 84186
    Prev
    Next
    INDEX
    Explanations

    Polish and Spanish words

    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_10/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
    Tetapi
    -2.17
    Sedangkan
    -1.84
    Послед
    -1.80
     patienter
    -1.77
    ܃
    -1.74
    这两
    -1.70
     pharmacie
    -1.66
     gari
    -1.63
     coq
    -1.60
     murale
    -1.57
    POSITIVE LOGITS
     "
    1.96
     
    1.77
     dando
    1.73
     exceedingly
    1.69
     denominado
    1.68
     usando
    1.65
     tzw
    1.62
     to
    1.59
     strikingly
    1.59
     "(
    1.57
    Activations Density 0.040%

    No Known Activations