© 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-65K
    7. 27344
    Prev
    Next
    INDEX
    Explanations

    identify concepts and examples

    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_65k_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
    ProductsStore
    0.42
     AGRICULTURAL
    0.41
    农业
    0.37
    另一方面
    0.35
    你也
    0.35
     生命
    0.35
    UserName
    0.34
    <unused2017>
    0.34
    FragmentManager
    0.34
     ресурс
    0.34
    POSITIVE LOGITS
     except
    0.49
     ignoring
    0.48
     facendo
    0.48
     providing
    0.48
     indiquant
    0.47
     decides
    0.47
     ensues
    0.46
     Fer
    0.46
    ↵↵
    0.46
     making
    0.46
    Activations Density 0.010%

    No Known Activations