© 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. 84880
    Prev
    Next
    INDEX
    Explanations

    numbers followed by '+'

    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
    際には
    -0.98
     notor
    -0.95
     espes
    -0.94
    часы
    -0.94
     pecuni
    -0.93
     connecter
    -0.93
     pels
    -0.91
     kwamen
    -0.91
     bril
    -0.90
    vább
    -0.90
    POSITIVE LOGITS
     subsequently
    0.82
     now
    0.81
    罚
    0.81
    Pers
    0.79
     APPELL
    0.78
     сталь
    0.77
     尚
    0.77
    את
    0.77
    ہ
    0.76
     provide
    0.75
    Activations Density 0.010%

    No Known Activations