© 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. 362
    Prev
    Next
    INDEX
    Explanations

    industry

    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
     and
    -1.91
     or
    -1.73
    年は
    -1.59
    以上です
    -1.59
    sitions
    -1.59
    That
    -1.57
    為主
    -1.53
    because
    -1.52
    although
    -1.52
    䊏
    -1.51
    POSITIVE LOGITS
     både
    1.66
     sinn
    1.61
     vols
    1.51
     لعبة
    1.47
    H
    1.45
     بعضی
    1.38
    髫
    1.38
     hef
    1.38
    茈
    1.37
    (
    1.35
    Activations Density 0.027%

    No Known Activations