© 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. 67456
    Prev
    Next
    INDEX
    Explanations

    CD followed by numbers or media types

    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
    1
    -2.98
    ⸩
    -2.44
    くちゃ
    -2.41
     gelb
    -2.39
     картинка
    -2.36
    婠
    -2.36
    lossians
    -2.31
    medriver
    -2.27
    🗹
    -2.20
    
    -2.14
    POSITIVE LOGITS
    ’
    3.72
    vaný
    2.23
     \&
    2.22
    }$,
    2.19
    ‏‏
    2.17
     The
    2.16
    )
    2.14
    }=
    2.13
     которая
    2.11
    玙
    2.11
    Activations Density 0.023%

    No Known Activations