© 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. 48301
    Prev
    Next
    INDEX
    Explanations

    introducing statements or explanations

    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
     ilyen
    -1.53
     Dingen
    -1.52
    </th>
    -1.40
    нией
    -1.37
    jà
    -1.33
     universitaria
    -1.32
    mdan
    -1.30
    苌
    -1.29
    delig
    -1.27
    POSITIVE LOGITS
     نمی
    1.66
    槩
    1.55
    ⏤
    1.55
    殽
    1.49
     there
    1.49
    terscotch
    1.41
     ;(
    1.39
    ⌵
    1.38
    ..(
    1.37
    without
    1.34
    Activations Density 0.006%

    No Known Activations