© 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. 64284
    Prev
    Next
    INDEX
    Explanations

    email headers or code comments

    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
     melk
    -0.80
     soát
    -0.75
     chè
    -0.75
    ryd
    -0.74
    zhen
    -0.74
     Kingsley
    -0.73
     sae
    -0.73
    unately
    -0.73
    samt
    -0.72
     schen
    -0.71
    POSITIVE LOGITS
     nachhal
    0.77
     _,
    0.75
     entstanden
    0.70
     celebratory
    0.69
    erobe
    0.68
    飘
    0.68
     Ə
    0.68
     मौ
    0.67
     corrugated
    0.67
     bestaan
    0.67
    Activations Density 0.003%

    No Known Activations