© 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. 107719
    Prev
    Next
    INDEX
    Explanations

    position words (anterior/posterior, former/latter)

    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
    AMED
    -0.91
    돋
    -0.84
    榄
    -0.83
    estudio
    -0.80
    biology
    -0.79
     optimale
    -0.78
    zeption
    -0.77
     bevat
    -0.77
    méable
    -0.77
     Karan
    -0.76
    POSITIVE LOGITS
    缀
    0.88
    cherichia
    0.85
    ém
    0.79
     metade
    0.77
     前
    0.76
     fling
    0.76
     後
    0.75
     impressão
    0.75
    期的
    0.74
    者
    0.73
    Activations Density 0.012%

    No Known Activations