© 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. 13249
    Prev
    Next
    INDEX
    Explanations

    short followed by a related descriptor

    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
    {
    -2.70
     of
    -2.34
     ehem
    -1.91
    嚳
    -1.89
    少なく
    -1.80
    StreetMap
    -1.77
    }
    -1.77
    裢
    -1.71
    迨
    -1.70
    ﮑ
    -1.66
    POSITIVE LOGITS
     که
    2.27
    1
    2.22
    憷
    2.06
    女
    1.91
    est
    1.82
    3
    1.80
     (<
    1.78
     fédé
    1.77
    𐐪
    1.77
    ish
    1.77
    Activations Density 0.028%

    No Known Activations