© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 87217
    Prev
    Next
    INDEX
    Explanations

    code imports and file paths

    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
    U
    -1.87
     with
    -1.80
    也是
    -1.66
    with
    -1.58
    A
    -1.55
    IA
    -1.51
    type
    -1.51
    in
    -1.48
    即使
    -1.46
    at
    -1.45
    POSITIVE LOGITS
    ﻻ
    1.66
    erschied
    1.60
    鑾
    1.56
    穑
    1.51
    pielen
    1.45
    ឪ
    1.45
    timm
    1.44
    zeln
    1.41
    颔
    1.41
    reloj
    1.40
    Activations Density 0.068%

    No Known Activations