© 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. 34-GEMMASCOPE-RES-131K
    7. 93110
    Prev
    Next
    INDEX
    Explanations

    academic/technical contexts

    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_34/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
    enguins
    -0.84
     impressed
    -0.82
    monte
    -0.79
    setOpaque
    -0.78
    aarrggbb
    -0.77
    発
    -0.75
    oleh
    -0.74
    ///<
    -0.74
    Odkazy
    -0.72
    ostock
    -0.71
    POSITIVE LOGITS
        
    0.94
            
    0.81
    botella
    0.81
    滂
    0.77
     propios
    0.72
    pozdrawiam
    0.72
     مذ
    0.72
    駅から
    0.72
    Conseils
    0.71
    uccino
    0.71
    Activations Density 0.144%

    No Known Activations