© 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. 84156
    Prev
    Next
    INDEX
    Explanations

    rental and questions

    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
     nap
    -0.84
    ālā
    -0.81
     طور
    -0.81
    numerus
    -0.80
    vább
    -0.79
    魄
    -0.78
    Muss
    -0.77
     beggars
    -0.76
    regime
    -0.76
    isst
    -0.75
    POSITIVE LOGITS
     rental
    0.91
     Rental
    0.86
     candidatura
    0.80
     rentals
    0.79
    Wenn
    0.76
    Esta
    0.76
     Hiz
    0.73
     Provincia
    0.73
    shadowRadius
    0.72
    į
    0.72
    Activations Density 0.009%

    No Known Activations