© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13754
    Prev
    Next
    INDEX
    Explanations

    month durations

    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
    寕
    -1.85
    درسة
    -1.80
    なんですが
    -1.79
    윔
    -1.79
     北市
    -1.78
     betrek
    -1.74
     peinado
    -1.74
     estadounid
    -1.74
     після
    -1.73
     eenvoudig
    -1.70
    POSITIVE LOGITS
    ↵
    2.73
    7
    2.28
    на
    2.28
    5
    2.23
    9
    2.14
     This
    2.13
    то
    1.97
     '
    1.96
    ↵↵↵↵
    1.96
    ли
    1.90
    Activations Density 0.022%

    No Known Activations