© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12142
    Prev
    Next
    INDEX
    Explanations

    title, description, example

    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
    ).
    -3.03
    霎
    -2.81
     utilizing
    -2.47
    酲
    -2.45
     exhaus
    -2.28
    ),
    -2.28
    
    -2.17
     кислота
    -2.11
    ☆☆☆☆☆
    -2.11
     summing
    -2.09
    POSITIVE LOGITS
    </h3>
    2.75
    珦
    2.59
     essayé
    2.59
    峩
    2.58
    很喜欢
    2.48
    家乡
    2.44
    这
    2.44
    这里
    2.34
     Which
    2.31
    uſe
    2.30
    Activations Density 0.002%

    No Known Activations