© 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. 144379
    Prev
    Next
    INDEX
    Explanations

    technical details and calculations

    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
     réaliser
    0.52
     către
    0.51
     supérieure
    0.49
     güzel
    0.47
     achieves
    0.47
     ottenere
    0.47
     plaît
    0.47
    🚋
    0.46
     estimates
    0.46
     achievable
    0.46
    POSITIVE LOGITS
    0
    0.54
    ле
    0.53
    <0x80>
    0.46
    ט
    0.46
    anged
    0.45
     बी
    0.45
    SE
    0.44
     ט
    0.44
    Ang
    0.43
     д
    0.43
    Activations Density 0.004%

    No Known Activations