© 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. 34-GEMMASCOPE-RES-131K
    7. 75842
    Prev
    Next
    INDEX
    Explanations

    return statements and continuation

    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
     recibiendo
    -0.82
     tota
    -0.79
     loca
    -0.77
    Regist
    -0.74
     získ
    -0.73
    첼
    -0.71
    检验
    -0.71
     extrem
    -0.70
    RECEIVE
    -0.70
    ໄ
    -0.69
    POSITIVE LOGITS
     continue
    1.94
    continue
    1.65
    继续
    1.55
     Continue
    1.53
    Continue
    1.47
    繼續
    1.42
     continuar
    1.40
     continues
    1.38
     continuing
    1.34
     continuation
    1.28
    Activations Density 0.016%

    No Known Activations