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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12015
    Prev
    Next
    INDEX
    Explanations

    Computing appliances, NAS OS

    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
     munich
    -1.35
     炖
    -1.35
     复古
    -1.34
    bước
    -1.34
    漼
    -1.30
     himo
    -1.30
     水墨
    -1.26
     jawa
    -1.23
     xj
    -1.22
    🧚
    -1.22
    POSITIVE LOGITS
    n
    1.52
    l
    1.44
    M
    1.41
    u
    1.41
    r
    1.37
    c
    1.36
    d
    1.31
    T
    1.31
    A
    1.30
    E
    1.30
    Activations Density 0.003%

    No Known Activations