© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110924
    Prev
    Next
    INDEX
    Explanations

    points and results

    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
    準
    -0.78
    andria
    -0.77
     Gerichte
    -0.74
     Palabra
    -0.74
    alei
    -0.73
     toekomst
    -0.72
    liege
    -0.71
     promesas
    -0.71
    пример
    -0.71
     assemblies
    -0.71
    POSITIVE LOGITS
     points
    2.59
    points
    2.11
    Points
    1.98
     Points
    1.73
    POINTS
    1.52
     puntos
    1.51
     POINTS
    1.45
     three
    1.38
    Result
    1.31
    pts
    1.28
    Activations Density 0.010%

    No Known Activations