© 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. 22-GEMMASCOPE-RES-131K
    4. 12282
    Prev
    Next
    INDEX
    Explanations

    apache license url parts

    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_22/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
    のでしょう
    -1.30
    のでしょうか
    -1.09
    ようになって
    -1.08
    
    -1.08
    のですか
    -1.06
    んでしょう
    -1.05
    はずです
    -1.04
    に入れ
    -1.04
     místě
    -1.03
     cerâmica
    -1.02
    POSITIVE LOGITS
    大さじ
    1.06
    などが
    1.05
     which
    1.02
    А
    1.02
     (
    0.98
    參考文獻
    0.94
     warung
    0.94
    ate
    0.94
     those
    0.93
     専用
    0.92
    Activations Density 0.019%

    No Known Activations