© 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. 118846
    Prev
    Next
    INDEX
    Explanations

    nothing followed by descriptor

    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
    ↵↵
    -1.80
     these
    -1.34
     involucrados
    -1.31
    遑
    -1.30
     favoritas
    -1.27
     mencionados
    -1.21
     takiej
    -1.20
     únicos
    -1.20
     the
    -1.17
     也
    -1.16
    POSITIVE LOGITS
     robić
    1.37
     awakeFromNib
    1.34
    unref
    1.33
     to
    1.33
    ilirsiniz
    1.30
    сла
    1.30
    assadors
    1.28
    venor
    1.27
    Before
    1.24
    takings
    1.24
    Activations Density 0.021%

    No Known Activations