© 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. 36169
    Prev
    Next
    INDEX
    Explanations

    special characters and code structures

    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
    itados
    -1.52
     fotográfica
    -1.48
    OBJETIVOS
    -1.42
     pintado
    -1.41
     kabát
    -1.37
     educativa
    -1.37
    Ventajas
    -1.34
    纍
    -1.33
     estampada
    -1.32
    Zubereitung
    -1.32
    POSITIVE LOGITS
    --
    1.13
    '
    1.12
    水が
    1.09
    ("
    1.06
     being
    1.03
    ローズ
    1.01
    änien
    1.00
    ,'
    1.00
     iedere
    0.99
     the
    0.98
    Activations Density 0.006%

    No Known Activations