Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 337
    Prev
    Next
    INDEX
    Explanations

    BILL, Hand, TGF growth

    np_acts-logits-general · gemini-2.5-flash-lite

    ASCII and Unicode character codes in technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    鹛
    -1.76
    Bukan
    -1.74
    赑
    -1.68
    媄
    -1.68
     生成
    -1.60
     africaine
    -1.58
     européenne
    -1.58
    Zubereitung
    -1.55
     Then
    -1.55
     miliki
    -1.55
    POSITIVE LOGITS
    ↵
    1.93
        
    1.63
    睥
    1.55
     ihre
    1.52
    </strong>
    1.52
    过去的
    1.51
     formidable
    1.50
    剜
    1.50
    widual
    1.41
     Особенно
    1.41
    Activations Density 0.008%

    No Known Activations