© 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. 35534
    Prev
    Next
    INDEX
    Explanations

    code and configuration options

    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
     semblables
    -0.97
     damski
    -0.94
    烔
    -0.91
     Índice
    -0.91
    nope
    -0.89
     prêts
    -0.89
    疒
    -0.88
    suitable
    -0.87
     Optics
    -0.87
     pantalones
    -0.86
    POSITIVE LOGITS
    asyon
    0.79
    特的
    0.79
    constants
    0.77
    2
    0.77
     и
    0.77
    ↵↵
    0.76
    anga
    0.75
     und
    0.73
     inclination
    0.72
    開口
    0.72
    Activations Density 0.001%

    No Known Activations