© 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. 68323
    Prev
    Next
    INDEX
    Explanations

    identifiers and special characters

    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
    User
    -1.07
    Data
    -1.05
    ">@
    -1.03
    Log
    -1.02
     установка
    -1.01
     من
    -1.00
     είναι
    -0.98
    ToMany
    -0.98
     définiti
    -0.98
    :✨
    -0.96
    POSITIVE LOGITS
     marrom
    1.15
    女性の
    1.13
     waarbij
    1.11
    Idem
    1.11
     nuestros
    1.11
    Especific
    1.09
    Partici
    1.08
    CÁ
    1.06
     añadido
    1.06
    Comentario
    1.05
    Activations Density 0.001%

    No Known Activations