© 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. 90085
    Prev
    Next
    INDEX
    Explanations

    Python libraries and frameworks

    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
    ksesta
    -0.96
     linens
    -0.76
     if
    -0.74
     would
    -0.71
     beneficiaries
    -0.71
    IMT
    -0.70
     menyelesaikan
    -0.70
    ากาศ
    -0.69
    TokenNameR
    -0.68
    tagonal
    -0.68
    POSITIVE LOGITS
     accidente
    0.85
    launched
    0.83
     open
    0.83
     navigu
    0.81
     interrom
    0.81
    ズル
    0.80
    が見える
    0.80
     кстати
    0.79
     ninguno
    0.78
    open
    0.77
    Activations Density 0.025%

    No Known Activations