© 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. 60077
    Prev
    Next
    INDEX
    Explanations

    Shrine Auditorium

    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
    ureux
    -0.82
    ERAL
    -0.82
     беремен
    -0.81
    ീ
    -0.80
    atex
    -0.77
    Ger
    -0.76
     Ger
    -0.76
     mic
    -0.75
    DB
    -0.75
    chet
    -0.75
    POSITIVE LOGITS
     Shr
    1.42
    Shr
    1.18
     Shrine
    1.13
     Scottish
    1.10
    Scottish
    1.09
     Fez
    0.89
    potent
    0.84
     fez
    0.81
     orthopedic
    0.79
     philanthropy
    0.75
    Activations Density 0.015%

    No Known Activations