© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11439
    Prev
    Next
    INDEX
    Explanations

    programming loops

    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_22/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
     even
    -1.09
    t
    -1.05
     auch
    -1.02
    に行った
    -1.00
     volverá
    -0.99
     \
    -0.97
    采取
    -0.96
     cả
    -0.95
     saben
    -0.91
     acidente
    -0.90
    POSITIVE LOGITS
    餿
    1.22
    PRESSION
    1.10
     naše
    1.10
     ſou
    1.10
     secondes
    1.07
    aları
    1.05
    ")}
    1.05
    uſe
    1.02
     avancer
    1.02
    房間
    1.02
    Activations Density 0.005%

    No Known Activations