© 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. 48121
    Prev
    Next
    INDEX
    Explanations

    probability calculations

    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
     مدى
    -0.78
     strtok
    -0.77
    shid
    -0.74
     Grüßen
    -0.73
     parece
    -0.73
     avenge
    -0.72
     seems
    -0.71
    maior
    -0.70
    وین
    -0.70
     Defensa
    -0.68
    POSITIVE LOGITS
    HYDR
    0.85
    épar
    0.82
    指着
    0.79
    辘
    0.79
     six
    0.79
    ulit
    0.79
     uniqu
    0.77
    owning
    0.77
     Snackbar
    0.77
     Pram
    0.76
    Activations Density 0.062%

    No Known Activations