© 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. 10-GEMMASCOPE-RES-131K
    4. 548
    Prev
    Next
    INDEX
    Explanations

    for X, Y and it is known that

    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
     to
    -2.06
     with
    -1.98
     as
    -1.91
     at
    -1.88
     so
    -1.77
     and
    -1.71
     both
    -1.44
     even
    -1.41
     WITH
    -1.40
    with
    -1.39
    POSITIVE LOGITS
     rigue
    1.55
     Niemand
    1.41
     jouets
    1.38
     boissons
    1.34
     lumières
    1.30
     âges
    1.30
     sabbia
    1.29
     sentí
    1.28
    ほとん
    1.27
    Medien
    1.27
    Activations Density 0.019%

    No Known Activations