© 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. 85066
    Prev
    Next
    INDEX
    Explanations

    commercial, release, source, spray, book

    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
    They
    -1.73
     Its
    -1.59
    Its
    -1.51
    Other
    -1.49
     really
    -1.44
    Their
    -1.41
     are
    -1.40
    ziná
    -1.38
     التي
    -1.37
     estreno
    -1.37
    POSITIVE LOGITS
     there
    1.38
     行き
    1.27
     neler
    1.25
     öner
    1.20
     綺麗
    1.19
     hie
    1.13
     地球
    1.11
    ydı
    1.11
    bür
    1.11
     to
    1.10
    Activations Density 0.298%

    No Known Activations