© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92488
    Prev
    Next
    INDEX
    Explanations

    fortune, company

    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
     ushort
    -1.10
     SEM
    -0.84
    Adjust
    -0.82
    lesssim
    -0.81
    énagement
    -0.81
    进程
    -0.80
    Qa
    -0.79
    kindle
    -0.79
    SEM
    -0.79
    UseVisualStyle
    -0.79
    POSITIVE LOGITS
    Fortune
    1.09
     Fortune
    0.98
     FORT
    0.95
     fortune
    0.84
     demain
    0.76
     fortuna
    0.74
    Suche
    0.74
     בר
    0.74
    fortune
    0.73
     Mv
    0.71
    Activations Density 0.009%

    No Known Activations