© 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. 10-GEMMASCOPE-RES-131K
    7. 124655
    Prev
    Next
    INDEX
    Explanations

    guide you toward a result

    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_10/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
     That
    -1.91
     at
    -1.44
     after
    -1.41
     EVERY
    -1.34
     что
    -1.34
     collaborative
    -1.33
     or
    -1.32
     саду
    -1.31
     hogy
    -1.31
     you
    -1.28
    POSITIVE LOGITS
    蹓
    1.78
     verrez
    1.74
     trouverez
    1.71
    guided
    1.67
    笵
    1.66
     deft
    1.60
    鹩
    1.58
    苙
    1.58
     recevrez
    1.57
    ين
    1.56
    Activations Density 0.018%

    No Known Activations