© 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. 30615
    Prev
    Next
    INDEX
    Explanations

    start of quoted speech

    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
    咳咳
    -1.33
    喏
    -0.91
    呸
    -0.84
     bianche
    -0.82
    からね
    -0.79
    好吗
    -0.76
    是啊
    -0.75
     Once
    -0.74
     Although
    -0.74
    呜呜
    -0.74
    POSITIVE LOGITS
     hey
    1.81
     oh
    1.80
     Hey
    1.68
     wow
    1.61
     Oh
    1.55
    Eh
    1.55
    wah
    1.55
    Oh
    1.54
     aw
    1.53
     Eh
    1.51
    Activations Density 0.016%

    No Known Activations