© 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. 10-GEMMASCOPE-RES-131K
    7. 70928
    Prev
    Next
    INDEX
    Explanations

    ionic liquids or GTX graphics cards

    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_10/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
    }
    -3.42
    t
    -3.00
    ,...
    -3.00
    ing
    -2.97
    y
    -2.95
    ar
    -2.80
    2
    -2.80
    --
    -2.80
     '
    -2.70
    ''
    -2.59
    POSITIVE LOGITS
    唎
    2.64
    ῞
    2.53
    ústria
    2.45
     });
    2.42
    鑁
    2.41
    ᠊
    2.41
     entidades
    2.39
    Ꭳ
    2.38
     aeron
    2.31
    nościo
    2.28
    Activations Density 0.029%

    No Known Activations