© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90746
    Prev
    Next
    INDEX
    Explanations

    automatic actions and states

    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
     to
    -1.88
    </strong>
    -1.84
     

    -1.76
     –
    -1.62
    </em>
    -1.53
     آنها
    -1.51
    螄
    -1.49
    кту
    -1.47
    古怪
    -1.46
    
    -1.45
    POSITIVE LOGITS
    For
    1.87
    哪裡
    1.80
    If
    1.78
    以上です
    1.74
    儼
    1.70
    線上
    1.68
    Check
    1.67
    From
    1.63
    有沒有
    1.61
     mógł
    1.61
    Activations Density 0.024%

    No Known Activations