© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12177
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables

    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
    Neue
    -1.69
    setzen
    -1.63
    venant
    -1.56
    İY
    -1.55
     الشاشة
    -1.54
     إدارة
    -1.48
    cension
    -1.45
     enth
    -1.45
    ные
    -1.44
     Новый
    -1.41
    POSITIVE LOGITS
     when
    2.63
     with
    2.36
     without
    2.19
     a
    2.16
     because
    1.84
     same
    1.77
     indicates
    1.74
    勦
    1.73
     determines
    1.73
     according
    1.70
    Activations Density 0.046%

    No Known Activations