© 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. 47719
    Prev
    Next
    INDEX
    Explanations

    from + downtown or distance

    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
    က်
    -0.79
     Haushalt
    -0.76
    vron
    -0.75
    暈
    -0.75
    Namen
    -0.75
    ágen
    -0.74
     boxeo
    -0.73
    animales
    -0.73
     fifty
    -0.72
     hundreds
    -0.71
    POSITIVE LOGITS
     beyond
    0.94
     distance
    0.90
    Downtown
    0.90
    beyond
    0.87
     floor
    0.86
     Downtown
    0.81
    DISTANCE
    0.79
     Distance
    0.79
    argb
    0.77
     慶
    0.76
    Activations Density 0.006%

    No Known Activations