© 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. 13167
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    ⅼ
    -1.13
     somebody
    -1.12
     everybody
    -1.05
    קב
    -1.02
     that
    -1.00
    AppCompatTheme
    -0.99
     anybody
    -0.94
     tuong
    -0.94
     everyone
    -0.93
    ローチ
    -0.93
    POSITIVE LOGITS
    Răsp
    1.17
    が
    1.14
    CÓMO
    1.10
    atör
    1.05
    alım
    1.03
    bản
    1.03
    は
    1.02
    Dislikes
    1.02
     exhilarating
    1.01
    xions
    0.95
    Activations Density 0.115%

    No Known Activations