© 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. 13076
    Prev
    Next
    INDEX
    Explanations

    submission and related contexts

    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
    y
    -3.45
    x
    -3.28
     was
    -2.92
     have
    -2.80
    k
    -2.75
     définiti
    -2.69
    -
    -2.63
    ]
    -2.59
    埽
    -2.58
     =
    -2.53
    POSITIVE LOGITS
    
    3.02
     améli
    2.97
     cliquer
    2.86
    狆
    2.84
    ፨
    2.83
     présenter
    2.81
    箆
    2.77
    罴
    2.73
    姈
    2.73
    鐔
    2.70
    Activations Density 0.007%

    No Known Activations