© 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. 33209
    Prev
    Next
    INDEX
    Explanations

    exception in thread

    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
    чис
    -0.88
     repression
    -0.86
    踞
    -0.85
     frische
    -0.77
    )!
    -0.76
    лаго
    -0.75
     clutches
    -0.75
     Eugenia
    -0.75
    rentino
    -0.74
    ону
    -0.74
    POSITIVE LOGITS
    のご紹介
    0.98
     kanad
    0.81
    ρον
    0.79
     mex
    0.79
    lesse
    0.77
     lese
    0.75
     biên
    0.75
    erex
    0.74
    ですので
    0.74
    quête
    0.73
    Activations Density 0.026%

    No Known Activations