© 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. 22-GEMMASCOPE-RES-131K
    7. 130033
    Prev
    Next
    INDEX
    Explanations

    POM / and Q:

    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_22/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
     juta
    -1.05
     Trauer
    -0.95
    loten
    -0.94
    traumatic
    -0.92
    Knit
    -0.90
    Hire
    -0.90
    pmatrix
    -0.89
    颔
    -0.87
     senhora
    -0.86
     према
    -0.86
    POSITIVE LOGITS
     SCE
    0.97
    !</
    0.90
     napkins
    0.88
     iedere
    0.86
     Underworld
    0.83
    ұ
    0.83
     unti
    0.83
    ,</
    0.83
     雑誌
    0.82
     classes
    0.82
    Activations Density 0.000%

    No Known Activations