© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93026
    Prev
    Next
    INDEX
    Explanations

    labels and categories

    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
    حوال
    -0.80
    くれない
    -0.77
    ♪♪
    -0.76
    Kapcsolódó
    -0.74
     Tink
    -0.73
     excès
    -0.72
    ţei
    -0.72
     neighbouring
    -0.71
    Cuer
    -0.71
     tournoi
    -0.70
    POSITIVE LOGITS
    ACTERS
    0.88
    jskiej
    0.85
     Text
    0.84
     disappoint
    0.79
    unan
    0.78
    unkel
    0.77
     Thursday
    0.77
    ̗
    0.77
    writers
    0.76
     flera
    0.75
    Activations Density 0.044%

    No Known Activations