© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202889
    Prev
    Next
    INDEX
    Explanations

    unexpected combinations or possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mios
    0.45
    irer
    0.43
     Trailers
    0.43
    </h3>
    0.43
    </h1>
    0.43
    </h5>
    0.43
    \]
    0.41
     utilises
    0.41
    лар
    0.41
    sudo
    0.41
    POSITIVE LOGITS
    密切
    0.50
     hyg
    0.49
     strategy
    0.49
     strategie
    0.48
     pediatrician
    0.47
     surfact
    0.47
     լ
    0.46
     pac
    0.46
    策略
    0.46
     gráfico
    0.46
    Activations Density 0.001%

    No Known Activations