© 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. 27258
    Prev
    Next
    INDEX
    Explanations

    Order, Blizzard, PWN, Best

    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
     Informações
    -0.96
     häm
    -0.94
     inspiradoras
    -0.94
     kommentar
    -0.94
    phylla
    -0.91
    què
    -0.91
     山
    -0.90
    ﱠ
    -0.90
    ፝
    -0.90
     dvou
    -0.90
    POSITIVE LOGITS
    が
    0.98
    は
    0.97
     caratteristiche
    0.97
    と
    0.93
    を
    0.92
    oria
    0.90
     ''
    0.85
     ܕ
    0.85
     zowel
    0.85
    zzer
    0.85
    Activations Density 0.000%

    No Known Activations