© 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. 102373
    Prev
    Next
    INDEX
    Explanations

    expect followed by outcome

    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
    }$
    -2.52
    ⼥
    -2.45
     étaient
    -2.44
    몭
    -2.39
     善
    -2.36
     réalité
    -2.34
    齪
    -2.34
    葙
    -2.30
     ダーク
    -2.27
     yüksek
    -2.25
    POSITIVE LOGITS
    {
    3.14
     größer
    2.69
    荩
    2.58
    t
    2.44
    2
    2.42
    al
    2.41
     I
    2.31
    ?
    2.30
    0
    2.25
    硖
    2.23
    Activations Density 0.018%

    No Known Activations