© 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. 99704
    Prev
    Next
    INDEX
    Explanations

    aimed at or directed at

    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
    impianto
    -0.98
     Bulldog
    -0.91
    irement
    -0.91
    üğü
    -0.91
     intérêt
    -0.87
     marinho
    -0.86
    blick
    -0.85
     unité
    -0.83
    Trat
    -0.83
    豨
    -0.83
    POSITIVE LOGITS
     toward
    1.73
     specifically
    1.73
     towards
    1.72
     squarely
    1.69
     at
    1.58
    specifically
    1.48
    toward
    1.37
     específicamente
    1.29
     Specifically
    1.27
     to
    1.27
    Activations Density 0.027%

    No Known Activations