© 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. 3875
    Prev
    Next
    INDEX
    Explanations

    foreign language or specific suffix

    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
     reuni
    -2.06
    omiast
    -1.97
    </sup>
    -1.96
    いえば
    -1.92
     entré
    -1.91
     périph
    -1.89
     proactively
    -1.89
     bré
    -1.89
     vedette
    -1.87
    宮崎
    -1.84
    POSITIVE LOGITS
    .
    2.19
     связанные
    1.94
    ↵↵
    1.91
     traditionellen
    1.88
     jiné
    1.84
    “:
    1.59
     worin
    1.59
    changers
    1.57
     in
    1.54
     swoich
    1.53
    Activations Density 0.079%

    No Known Activations