© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104574
    Prev
    Next
    INDEX
    Explanations

    indirectly referenced data

    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
    Norwegian
    -0.79
     prisión
    -0.75
    momento
    -0.75
     erz
    -0.73
     clueless
    -0.72
     divertidos
    -0.71
    Ľ
    -0.71
     módulos
    -0.71
     enlaces
    -0.69
    masının
    -0.69
    POSITIVE LOGITS
    indirect
    1.30
     indirect
    1.26
    Indirect
    1.23
     indirectly
    1.17
     Indirect
    1.07
     Therefore
    1.02
     indirec
    0.94
    可以直接
    0.93
     directamente
    0.92
     ikut
    0.91
    Activations Density 0.081%

    No Known Activations