© 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. 27625
    Prev
    Next
    INDEX
    Explanations

    events and names

    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
    зия
    -1.12
    phosa
    -1.02
    рация
    -0.98
    ilités
    -0.95
    さん
    -0.94
    肽
    -0.94
     dė
    -0.92
    旳
    -0.91
    资料
    -0.89
    oweit
    -0.89
    POSITIVE LOGITS
     ,
    1.18
     such
    1.06
    ,...
    1.00
     aporta
    0.98
     […]
    0.96
    Rozmiar
    0.95
    [...]
    0.92
     [...]
    0.92
    ...
    0.91
    ,\\
    0.91
    Activations Density 0.146%

    No Known Activations