© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78010
    Prev
    Next
    INDEX
    Explanations

    things coming together

    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
    reurs
    -0.96
    嬲
    -0.83
    াঁ
    -0.81
    amesh
    -0.77
    Loai
    -0.74
    ász
    -0.73
    Abbreviations
    -0.73
    པའི་
    -0.73
    udges
    -0.73
    丁寧に
    -0.72
    POSITIVE LOGITS
     together
    8.44
    together
    5.94
    Together
    5.41
     Together
    5.22
     вместе
    4.56
     insieme
    4.22
     juntos
    4.19
     TOGETHER
    3.97
     zusammen
    3.83
    一起
    3.67
    Activations Density 0.128%

    No Known Activations