© 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. 10-GEMMASCOPE-RES-131K
    7. 13569
    Prev
    Next
    INDEX
    Explanations

    households, firms, and spells

    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
    -1.64
    5
    -1.45
    ,”
    -1.45
     itali
    -1.35
     justiça
    -1.34
     everybody
    -1.31
    most
    -1.31
     如
    -1.30
    after
    -1.28
     gröss
    -1.28
    POSITIVE LOGITS
    ейчас
    1.61
    ࿚
    1.57
     sentada
    1.52
     acompañada
    1.51
     fabriqué
    1.50
    рыва
    1.48
     desnuda
    1.48
    DialogContent
    1.45
     acompañado
    1.44
    phene
    1.44
    Activations Density 0.099%

    No Known Activations