© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 122
    Prev
    Next
    INDEX
    Explanations

    metro station

    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
     Roughly
    -1.44
     However
    -1.35
    but
    -1.34
    一方で
    -1.32
    That
    -1.30
     Typically
    -1.28
    截至
    -1.28
     اگر
    -1.27
     Nonetheless
    -1.25
     Würde
    -1.24
    POSITIVE LOGITS
    itzung
    1.42
    ’,
    1.41
    --}}
    1.35
     terceira
    1.34
     menangis
    1.33
     soldat
    1.32
     programmation
    1.32
    軚
    1.31
    cerpts
    1.30
     pesa
    1.30
    Activations Density 0.029%

    No Known Activations