© 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. 63596
    Prev
    Next
    INDEX
    Explanations

    graph adjacency list

    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
     frutti
    -0.81
    NESOTA
    -0.79
    ஈ
    -0.76
    උ
    -0.71
    ("").
    -0.70
    ريب
    -0.69
    𝖚
    -0.67
    ]+=
    -0.66
    ToLeft
    -0.66
     retirement
    -0.65
    POSITIVE LOGITS
     adjacency
    1.54
     graph
    1.32
     adjacent
    1.32
     adj
    1.26
     vertex
    1.26
    vertex
    1.22
    graph
    1.22
     vertices
    1.20
     edges
    1.16
     edge
    1.13
    Activations Density 0.022%

    No Known Activations