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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 446
    Prev
    Next
    INDEX
    Explanations

    checks for null or nil

    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_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
    3
    -1.48
    ヤバ
    -1.47
     estão
    -1.41
     have
    -1.41
    ︲
    -1.41
    ,
    -1.39
     obtiene
    -1.39
     bús
    -1.38
    鬟
    -1.38
     proporciona
    -1.37
    POSITIVE LOGITS
    ₽
    1.38
    reurs
    1.36
     new
    1.35
    erializer
    1.34
     one
    1.33
    %;
    
    1.32
    yeur
    1.32
    龵
    1.31
    ecology
    1.31
    _));
    1.28
    Activations Density 0.005%

    No Known Activations