© 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. 31433
    Prev
    Next
    INDEX
    Explanations

    hanging / suspension

    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
    PLATE
    -0.81
     windings
    -0.77
    ندگان
    -0.72
     circ
    -0.69
     flattening
    -0.69
     Corinth
    -0.69
     playstation
    -0.69
     dvd
    -0.69
     Tijuana
    -0.69
     GIG
    -0.68
    POSITIVE LOGITS
     pods
    1.13
     подве
    1.05
    挂
    1.01
     pod
    0.97
     pyl
    0.96
     hanging
    0.91
     treo
    0.90
     hanged
    0.88
     suspension
    0.88
     挂
    0.85
    Activations Density 0.017%

    No Known Activations