© 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. 22-GEMMASCOPE-RES-131K
    7. 11260
    Prev
    Next
    INDEX
    Explanations

    academic conferences and symposia

    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
    N
    -1.66
     a
    -1.48
    Y
    -1.46
    J
    -1.42
     first
    -1.40
    Z
    -1.38
    A
    -1.37
    X
    -1.35
    V
    -1.31
     and
    -1.30
    POSITIVE LOGITS
    Oby
    1.58
    Rumah
    1.52
     rajut
    1.50
    內容簡介
    1.46
     作り方
    1.46
     symbole
    1.43
     perak
    1.43
    1.42
    Waga
    1.40
    Jawab
    1.39
    Activations Density 0.007%

    No Known Activations