© 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. 10-GEMMASCOPE-RES-131K
    7. 48113
    Prev
    Next
    INDEX
    Explanations

    child, son, daughter

    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
    难受
    -1.30
    Ꭱ
    -1.16
     would
    -1.05
    nt
    -1.03
     italiens
    -0.98
    ̀i
    -0.97
    pośred
    -0.96
    lastung
    -0.95
     вид
    -0.94
    眶
    -0.94
    POSITIVE LOGITS
     berbasis
    1.16
    беріга
    1.16
    houettes
    1.13
     prossima
    1.13
     alerg
    1.10
     bendera
    1.09
     ujung
    1.08
    esimo
    1.07
     jajaran
    1.06
     stasiun
    1.05
    Activations Density 0.059%

    No Known Activations