© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 9572
    Prev
    Next
    INDEX
    Explanations

    surface geometry and analogies

    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_16k_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
     acceptability
    0.46
    ∃
    0.45
    ᴿ
    0.44
    directive
    0.43
    疑問
    0.43
     RMSE
    0.43
     Knowles
    0.43
     проблемой
    0.42
    ायल
    0.42
    ッセージ
    0.42
    POSITIVE LOGITS
     submanifold
    0.46
     Holog
    0.45
     brane
    0.44
     manifold
    0.44
     maritime
    0.44
     seaf
    0.43
     holog
    0.43
    ){}^
    0.43
     holomorphic
    0.42
    Surface
    0.42
    Activations Density 0.147%

    No Known Activations