© 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. 118756
    Prev
    Next
    INDEX
    Explanations

    numbers and code snippets

    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
     really
    -0.78
    shp
    -0.78
     where
    -0.78
     करके
    -0.77
     tribes
    -0.77
     apre
    -0.77
     действительно
    -0.77
    アレルギー
    -0.76
    ربای
    -0.76
    녀
    -0.74
    POSITIVE LOGITS
    tata
    0.81
     deline
    0.73
     ressemb
    0.70
    말
    0.70
     backs
    0.69
     alamy
    0.68
     сообщает
    0.68
    
    0.68
     Muf
    0.67
     mcqueen
    0.67
    Activations Density 0.000%

    No Known Activations