© 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. 130175
    Prev
    Next
    INDEX
    Explanations

    code snippets or paths

    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
     if
    -1.05
     or
    -1.01
     TAMBÉM
    -1.00
     not
    -0.99
     vermelhas
    -0.97
     allowing
    -0.96
    ñones
    -0.96
     four
    -0.95
    himu
    -0.94
     frantic
    -0.94
    POSITIVE LOGITS
    项目的
    1.04
    啐
    1.02
     overarching
    1.00
    each
    1.00
    拍了拍
    0.99
    癱
    0.96
     momentous
    0.96
    這邊
    0.95
     esfuerzos
    0.94
     astounding
    0.93
    Activations Density 0.003%

    No Known Activations