Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 354
    Prev
    Next
    INDEX
    Explanations

    good thing

    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_10/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
    -"
    -1.52
     maquillage
    -1.48
     STILL
    -1.47
    ſelves
    -1.45
    ACCIÓN
    -1.43
     cír
    -1.41
     espagnol
    -1.41
     kumaş
    -1.41
     ">
    -1.40
     bré
    -1.40
    POSITIVE LOGITS
     they
    2.02
    izowane
    1.41
     secu
    1.39
     några
    1.35
     cuadrada
    1.25
     Univer
    1.24
     meis
    1.22
     Minist
    1.21
    能够
    1.21
     of
    1.21
    Activations Density 0.007%

    No Known Activations