© 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. 85998
    Prev
    Next
    INDEX
    Explanations

    i want

    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
    </
    -1.66
    -1.59
     "
    -1.43
    ṡ
    -1.40
    cof
    -1.38
    ane
    -1.38
               
    -1.38
    地说道
    -1.34
    obut
    -1.34
                         
    -1.34
    POSITIVE LOGITS
     since
    1.59
    Beberapa
    1.54
    涔
    1.51
    Ketua
    1.49
    Jeudi
    1.45
     of
    1.42
    Sebagai
    1.41
    Sudah
    1.41
    数百
    1.41
    Seperti
    1.38
    Activations Density 0.096%
    No Known Activations