© 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. 34-GEMMASCOPE-RES-131K
    7. 76887
    Prev
    Next
    INDEX
    Explanations

    elif, whether, either

    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
     anywhere
    -0.90
     excluding
    -0.82
     like
    -0.74
    }</
    -0.73
    */}
    -0.73
     depending
    -0.73
    NIGHT
    -0.73
    mojo
    -0.72
    ìm
    -0.71
     Anywhere
    -0.71
    POSITIVE LOGITS
     whether
    1.06
     Whether
    0.91
        
    0.89
     either
    0.86
    elif
    0.81
            
    0.80
    gating
    0.79
     eleições
    0.79
    atelyn
    0.77
     nearby
    0.77
    Activations Density 0.013%

    No Known Activations