© 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. 102920
    Prev
    Next
    INDEX
    Explanations

    clip / paperclip

    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
    :')
    -0.87
    梅花
    -0.78
     ц
    -0.78
     Pater
    -0.77
     attackers
    -0.75
    чее
    -0.75
     Thief
    -0.73
    地
    -0.73
    ůže
    -0.72
     แก
    -0.72
    POSITIVE LOGITS
    Cli
    1.35
     cli
    1.30
     Cli
    1.19
    cli
    1.18
    Clip
    1.05
     Clip
    1.03
     clip
    0.98
     Кли
    0.96
     clips
    0.91
     unui
    0.87
    Activations Density 0.005%

    No Known Activations