© 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. 99759
    Prev
    Next
    INDEX
    Explanations

    symbol indicating meaning or context

    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
     מוצ
    -0.85
    ược
    -0.85
    takings
    -0.84
    ManyToOne
    -0.81
    ๔
    -0.80
    Ọ
    -0.79
    posições
    -0.78
     which
    -0.78
    vint
    -0.78
    лія
    -0.77
    POSITIVE LOGITS
     indicates
    1.45
     indicate
    1.40
     denotes
    1.24
     denote
    1.18
    Indicates
    1.17
     indicating
    1.09
     indication
    1.07
     Den
    1.04
     denoting
    0.98
    Den
    0.98
    Activations Density 0.009%

    No Known Activations