© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8893
    Prev
    Next
    INDEX
    Explanations

    breathable fabric, key dimensions, show different

    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
    বহুল
    0.46
     Juda
    0.44
    大多數
    0.44
    🥬
    0.43
    大多数
    0.42
     মাত্র
    0.42
    ?
    0.42
    或
    0.42
    /
    0.41
     legitimately
    0.41
    POSITIVE LOGITS
    Deletion
    0.50
     ഡോ
    0.49
    ێنی
    0.49
    deletion
    0.48
    Reconnect
    0.46
     काग
    0.44
    LQ
    0.44
    Rain
    0.44
    0
    0.44
    Values
    0.44
    Activations Density 0.001%

    No Known Activations