© 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. 25724
    Prev
    Next
    INDEX
    Explanations

    issue with specific problems

    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
     ответа
    -0.86
    喲
    -0.84
     основные
    -0.84
    文獻
    -0.84
    唷
    -0.84
    ポイントは
    -0.82
     saveur
    -0.82
    つまり
    -0.82
    usky
    -0.81
     새
    -0.80
    POSITIVE LOGITS
     driven
    1.04
     Driven
    0.96
     IDENTIFICATION
    0.94
     identification
    0.90
    mą
    0.87
    Ẽ
    0.87
     detection
    0.85
    driven
    0.84
     fatigue
    0.83
     kitap
    0.83
    Activations Density 0.159%

    No Known Activations