© 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. 28112
    Prev
    Next
    INDEX
    Explanations

    author

    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
    ’
    -3.78
    ",
    -2.97
    "
    -2.77
    ll
    -2.50
    )
    -2.41
    苤
    -2.23
    ;
    -2.17
    ',
    -2.14
    ,'
    -2.14
    を使って
    -2.13
    POSITIVE LOGITS
    Ꮉ
    2.98
    糹
    2.84
    𖡼
    2.75
     作り方
    2.67
    鰱
    2.66
    ⸒
    2.63
    𐐪
    2.58
    锷
    2.48
    彣
    2.45
     शुर
    2.36
    Activations Density 0.042%

    No Known Activations