© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109888
    Prev
    Next
    INDEX
    Explanations

    Nigeria Puts, Sal Valentine, #Updated

    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_34/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
    ᴼ
    -1.02
    عادة
    -0.97
    "+
    
    -0.96
    Quite
    -0.94
    '__
    -0.94
    typeof
    -0.90
    ३
    -0.90
    '`
    -0.90
    Both
    -0.89
    isim
    -0.88
    POSITIVE LOGITS
     ↑
    1.42
    などが
    1.06
    などは
    1.00
    Джерела
    0.99
    などを
    0.93
     ^
    0.89
     다른
    0.86
     visitare
    0.85
    抬头
    0.85
    (,
    0.84
    Activations Density 0.000%

    No Known Activations