© 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. 10-GEMMASCOPE-RES-131K
    7. 1231
    Prev
    Next
    INDEX
    Explanations

    numbers around 150s

    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_10/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
    '
    -3.22
    ‘
    -2.23
    }
    -2.22
     
    -1.92
    ent
    -1.86
    şört
    -1.81
    但他
    -1.79
     in
    -1.72
    ]
    -1.69
    ",
    -1.68
    POSITIVE LOGITS
     Когда
    2.14
    慤
    2.11
     cuando
    2.02
    跄
    1.99
    3
    1.98
     Gründe
    1.95
    雳
    1.93
     когда
    1.93
    んですが
    1.84
     ถ้า
    1.83
    Activations Density 0.063%

    No Known Activations