© 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. 59110
    Prev
    Next
    INDEX
    Explanations

    exclusive video descriptions

    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
    おま
    -0.87
    你这个
    -0.82
     anaknya
    -0.81
    وقات
    -0.77
     because
    -0.76
     журнали
    -0.76
    افر
    -0.75
     their
    -0.73
    روع
    -0.73
     tomate
    -0.73
    POSITIVE LOGITS
    VIDEO
    1.81
     VIDEO
    1.68
    WATCH
    1.58
     WATCH
    1.55
     analysis
    1.46
    Opinion
    1.45
     video
    1.43
     Opinion
    1.42
     opinion
    1.41
    OPINION
    1.41
    Activations Density 0.042%

    No Known Activations