© 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. 69907
    Prev
    Next
    INDEX
    Explanations

    rough and following words

    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
    CFS
    -0.73
    Xiv
    -0.71
     stimulation
    -0.71
     Castor
    -0.69
     Stimulation
    -0.67
    zole
    -0.66
     Carcass
    -0.66
    玟
    -0.66
     UserService
    -0.66
     Centrale
    -0.65
    POSITIVE LOGITS
     Rose
    0.67
    hlin
    0.66
    PointF
    0.65
     constru
    0.65
    境
    0.64
     sle
    0.64
    transform
    0.64
     bintang
    0.64
     Non
    0.63
     Jetzt
    0.63
    Activations Density 0.062%

    No Known Activations