© 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. 34-GEMMASCOPE-RES-131K
    7. 70182
    Prev
    Next
    INDEX
    Explanations

    Q: or Making the

    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
    Concerning
    -0.86
    Nachdem
    -0.84
    Whilst
    -0.79
     schreiben
    -0.79
     último
    -0.79
     HAVE
    -0.78
    ="$(
    -0.78
     mismos
    -0.76
     rem
    -0.75
    除了
    -0.75
    POSITIVE LOGITS
     ingrediente
    0.91
     crê
    0.90
    !;
    0.87
    거나
    0.86
     Coro
    0.85
     infrar
    0.85
     HAST
    0.85
     tokenId
    0.84
     reputa
    0.83
     sirop
    0.82
    Activations Density 0.000%

    No Known Activations