© 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. 79960
    Prev
    Next
    INDEX
    Explanations

    and thenand followed byand conjunctionand punctuation

    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
     also
    -1.50
     even
    -1.16
    Moda
    -1.12
     but
    -1.06
    ėja
    -1.01
     any
    -1.00
     jeg
    -0.99
    视为
    -0.98
    esine
    -0.95
    Ответить
    -0.93
    POSITIVE LOGITS
     to
    1.88
     vorüber
    1.18
     namentlich
    1.09
    手中的
    1.08
     لإ
    1.07
     чтобы
    1.06
     gänzlich
    1.05
     You
    1.03
    once
    1.02
     Try
    1.02
    Activations Density 0.067%

    No Known Activations