© 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. 78167
    Prev
    Next
    INDEX
    Explanations

    cosmological constant and parameters

    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
    OBJETIVOS
    -0.81
    高橋
    -0.71
    ğaz
    -0.69
    一心
    -0.69
     rowspan
    -0.67
    reducers
    -0.67
     knockout
    -0.67
     System
    -0.65
     تمر
    -0.65
    ждается
    -0.65
    POSITIVE LOGITS
     cosmological
    1.61
     Cosmo
    1.06
    cosmo
    0.98
     constant
    0.98
    Cosmo
    0.91
    constant
    0.91
    
    0.88
    ZERO
    0.87
    Constant
    0.87
     Lambda
    0.85
    Activations Density 0.046%

    No Known Activations