© 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. 22-GEMMASCOPE-RES-131K
    7. 84268
    Prev
    Next
    INDEX
    Explanations

    loading pages or elements

    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_22/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
    piecze
    -1.04
    драт
    -1.02
    Lastly
    -0.98
     Lastly
    -0.96
    Schritt
    -0.96
    涝
    -0.95
    }}_
    -0.95
     kaž
    -0.93
    cnia
    -0.92
     crea
    -0.91
    POSITIVE LOGITS
     switch
    0.92
     Chosen
    0.91
    ย์
    0.88
     Choice
    0.85
    更换
    0.84
     corresponding
    0.83
     соответству
    0.82
    ([],
    0.82
     INJ
    0.81
    Chosen
    0.80
    Activations Density 0.017%

    No Known Activations