© 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. 120164
    Prev
    Next
    INDEX
    Explanations

    commercially available items

    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
     indiví
    -1.76
    苼
    -1.69
    埽
    -1.62
     they
    -1.54
     then
    -1.46
    桫
    -1.46
    𓍊
    -1.43
    .’”
    -1.42
    ᾐ
    -1.42
     estim
    -1.41
    POSITIVE LOGITS
    ↵↵
    1.74
    a
    1.65
    o
    1.55
     alimentare
    1.49
     name
    1.40
     から
    1.36
     anspruchs
    1.36
    melidir
    1.34
    之际
    1.34
     aportar
    1.30
    Activations Density 0.035%

    No Known Activations