© 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. 76679
    Prev
    Next
    INDEX
    Explanations

    shaped, plate-like, or strip-like forms

    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
    Pollution
    -0.77
     erklärte
    -0.77
     özellikleri
    -0.76
     assistir
    -0.75
     belirt
    -0.75
     пы
    -0.75
    ܼ
    -0.75
     tubules
    -0.74
    Wales
    -0.74
    powder
    -0.73
    POSITIVE LOGITS
    状
    1.88
    狀
    1.51
    haped
    1.41
    förm
    1.16
     shaped
    1.12
     状
    1.10
     or
    1.05
    shaped
    1.04
     format
    1.02
     form
    0.96
    Activations Density 0.204%

    No Known Activations