© 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. 111071
    Prev
    Next
    INDEX
    Explanations

    something has changed

    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
    e
    -3.13
    ৪
    -2.69
    ྵ
    -2.42
    ⢓
    -2.34
    k
    -2.33
    います
    -2.28
    u
    -2.22
     洗濯
    -2.11
     尔
    -2.09
    ızlık
    -2.09
    POSITIVE LOGITS
    '
    4.16
     ツリー
    2.64
     changed
    2.64
    With
    2.58
     лишь
    2.48
    饪
    2.48
    .
    2.45
    of
    2.42
    は
    2.39
    Apparently
    2.28
    Activations Density 0.006%

    No Known Activations