© 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. 1405
    Prev
    Next
    INDEX
    Explanations

    paper or article titles

    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
    aussi
    -1.35
     Особенно
    -1.28
    皷
    -1.20
     praktisch
    -1.14
     Según
    -1.13
     imó
    -1.10
     praktische
    -1.09
     précédent
    -1.08
     chad
    -1.07
     .........
    -1.06
    POSITIVE LOGITS
    <eos>
    1.67
    ↵↵↵↵
    1.25
    ↵↵↵↵↵
    1.18
     beautiful
    1.16
     on
    1.13
    ↵↵↵
    1.13
    ↵↵↵↵↵↵↵↵↵
    1.13
    ↵↵↵↵↵↵↵
    1.11
     new
    1.10
    ↵↵↵↵↵↵↵↵
    1.09
    Activations Density 0.007%

    No Known Activations