© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25919
    Prev
    Next
    INDEX
    Explanations

    probability and stochastic processes

    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
    เที่ยว
    -0.94
     fertiliz
    -0.85
     peppermint
    -0.82
    łek
    -0.82
    벚
    -0.81
     neighbourhoods
    -0.81
     自動車
    -0.80
    Cedar
    -0.80
    受
    -0.80
     proxy
    -0.79
    POSITIVE LOGITS
    haka
    0.79
     esso
    0.75
    hahaha
    0.75
    hahahaha
    0.75
    ventus
    0.73
     Série
    0.71
     Rés
    0.69
     warto
    0.69
     modelli
    0.69
     torta
    0.68
    Activations Density 0.016%

    No Known Activations