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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13363
    Prev
    Next
    INDEX
    Explanations

    creative commons licenses

    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
    </strong>
    -3.38
    ’
    -2.91
        
    -2.66
    s
    -2.39
    er
    -2.39
    }$
    -2.39
    {~
    -2.38
             
    -2.22
     lack
    -2.20
    画家
    -2.13
    POSITIVE LOGITS
    
    2.42
    own
    2.27
     syste
    2.23
     beide
    2.23
    柃
    2.16
    檮
    2.13
    怼
    2.06
    𓇼
    2.05
     และ
    2.05
    搅拌
    1.98
    Activations Density 0.003%

    No Known Activations