© 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. 41526
    Prev
    Next
    INDEX
    Explanations

    attempts to

    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
    ↓↓↓
    -2.02
     ↓
    -1.98
    笕
    -1.93
     fêtes
    -1.84
    With
    -1.83
    官網
    -1.83
     →
    -1.79
    抜粋
    -1.76
    ====
    -1.74
     プラス
    -1.73
    POSITIVE LOGITS
    ”.
    2.06
    ↵↵
    1.83
     insgesamt
    1.68
    魃
    1.66
    ,”
    1.63
    ”
    1.61
     lukewarm
    1.56
     Keeping
    1.55
     Of
    1.53
    微微
    1.53
    Activations Density 0.035%

    No Known Activations