© 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. 31230
    Prev
    Next
    INDEX
    Explanations

    hanging

    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
     desorption
    -0.76
     közé
    -0.75
    ρή
    -0.72
    siery
    -0.70
    ườ
    -0.69
     finalidad
    -0.68
    
    -0.68
    vase
    -0.67
     euró
    -0.66
    vosť
    -0.66
    POSITIVE LOGITS
     hang
    4.66
     hanged
    4.41
     hanging
    4.31
     Hang
    3.83
    hang
    3.75
     Hanging
    3.75
    Hang
    3.73
     hangs
    3.73
    Hanging
    3.72
     HANG
    3.67
    Activations Density 0.034%

    No Known Activations