© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118823
    Prev
    Next
    INDEX
    Explanations

    `#include` or `package`

    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_34/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
    ਦ
    -0.75
     라이
    -0.73
    ock
    -0.71
    找到
    -0.70
    kowych
    -0.69
    てん
    -0.69
    ไล
    -0.68
    猖
    -0.68
     Ř
    -0.68
    绦
    -0.68
    POSITIVE LOGITS
    trin
    0.70
    momentum
    0.68
     ザ
    0.66
    Contacts
    0.66
     Decks
    0.65
     veckan
    0.64
     Adopt
    0.64
     Renewed
    0.63
     тип
    0.63
    call
    0.63
    Activations Density 0.086%

    No Known Activations