© 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. 42086
    Prev
    Next
    INDEX
    Explanations

    Chanel, OBE, Coco

    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
    
    -2.64
     トラベル
    -2.48
    );
    -2.41
    珰
    -2.41
    !”
    -2.34
    鼴
    -2.28
    ﮯ
    -2.22
     handful
    -2.20
     worthwhile
    -2.17
     enjoyable
    -2.16
    POSITIVE LOGITS
     Chanel
    2.41
    which
    2.16
    いだ
    2.14
    }$
    2.11
    ход
    2.09
     tuvimos
    2.09
    あり
    2.05
     '
    2.03
    埽
    2.02
    酔
    2.00
    Activations Density 0.000%

    No Known Activations