© 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. 43154
    Prev
    Next
    INDEX
    Explanations

    Ada Lovelace, grand hotel, jason, rasp, lazy

    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
    葯
    -2.58
    ݮ
    -2.47
    ݯ
    -2.31
     всѣ
    -2.30
    ㈮
    -2.27
    ſu
    -2.22
     éditoriale
    -2.20
    
    -2.19
    罅
    -2.14
    踅
    -2.09
    POSITIVE LOGITS
    ’
    3.48
     We
    3.39
    {
    3.03
    ]
    2.77
    a
    2.50
    jenige
    2.48
    }
    2.41
     was
    2.39
    `
    2.34
     are
    2.33
    Activations Density 0.001%

    No Known Activations