© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91399
    Prev
    Next
    INDEX
    Explanations

    website about sections

    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
    是大
    -0.91
     tỷ
    -0.91
     使っ
    -0.90
     sadece
    -0.88
    greens
    -0.88
    of
    -0.87
     pomaga
    -0.86
    owanie
    -0.84
     dijeron
    -0.84
     agradec
    -0.83
    POSITIVE LOGITS
    aleb
    1.28
    łosi
    1.01
     myself
    0.99
     féminin
    0.98
    尚
    0.90
    TimeZone
    0.89
    rika
    0.88
    🤝
    0.88
    大声
    0.87
    blank
    0.86
    Activations Density 0.018%

    No Known Activations