© 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. 76345
    Prev
    Next
    INDEX
    Explanations

    majority of

    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
     minimization
    -0.94
     toate
    -0.93
    hej
    -0.91
     materialism
    -0.88
    جميع
    -0.84
    诞
    -0.84
    аз
    -0.82
    tencent
    -0.82
     дают
    -0.81
     niño
    -0.81
    POSITIVE LOGITS
     opinion
    1.53
     of
    1.39
     vote
    1.30
     gruppe
    1.12
     (>
    1.09
     bloc
    1.05
    opinion
    1.05
    意見
    1.04
     consensus
    1.02
     мнение
    1.01
    Activations Density 0.014%

    No Known Activations