© 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. 12304
    Prev
    Next
    INDEX
    Explanations

    closing code punctuation

    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
     here
    -1.01
    多少钱
    -0.99
     publiés
    -0.98
    這裡
    -0.98
     linken
    -0.93
    が
    -0.92
    呟
    -0.91
     heridos
    -0.90
     توضی
    -0.89
    ensed
    -0.89
    POSITIVE LOGITS
    )+\
    1.07
     []:
    0.99
    づけ
    0.95
     believes
    0.93
    >+</
    0.91
    );
    
    0.91
    }],
    
    0.91
     if
    0.90
    OREM
    0.89
     belangrij
    0.87
    Activations Density 0.002%

    No Known Activations