© 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. 81645
    Prev
    Next
    INDEX
    Explanations

    code blocks and declarations

    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
     zac
    -0.76
     then
    -0.72
     Zed
    -0.71
    师兄
    -0.70
    非洲
    -0.69
    饲
    -0.69
    Cher
    -0.68
     safety
    -0.68
    зино
    -0.68
     Safari
    -0.68
    POSITIVE LOGITS
    alnız
    1.02
     indentation
    0.94
    setdefault
    0.89
     Babcock
    0.84
     sprout
    0.81
    ifx
    0.81
    artement
    0.81
     smtp
    0.80
    ppincott
    0.80
     člove
    0.79
    Activations Density 0.007%

    No Known Activations