© 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. 93337
    Prev
    Next
    INDEX
    Explanations

    panel, widget, group

    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
     salari
    -0.82
     Poznań
    -0.79
     helle
    -0.79
     geometr
    -0.79
     软
    -0.78
    继续阅读
    -0.77
     derin
    -0.76
     baden
    -0.76
     sonnen
    -0.75
     ſhe
    -0.75
    POSITIVE LOGITS
     tools
    1.02
    tools
    0.86
     herramientas
    0.85
    patra
    0.81
    ToMove
    0.80
    веро
    0.77
     collapse
    0.75
     removals
    0.74
     move
    0.72
    ว์
    0.72
    Activations Density 0.005%

    No Known Activations