© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68344
    Prev
    Next
    INDEX
    Explanations

    however,

    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
     about
    -2.09
    どうやら
    -1.67
    に行ってきました
    -1.55
     essenziale
    -1.52
     illustrated
    -1.48
    たび
    -1.48
    ꒦
    -1.47
     통해
    -1.46
    aimana
    -1.45
    田舎
    -1.44
    POSITIVE LOGITS
    ʻ
    1.84
    ↵
    1.73
    Of
    1.67
     många
    1.66
                          
    1.66
    6
    1.66
            
    1.65
              
    1.63
    ↵↵
    1.60
    1
    1.60
    Activations Density 0.026%

    No Known Activations