© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 165600
    Prev
    Next
    INDEX
    Explanations

    D-Mannose mining Tree blog

    np_acts-logits-general · gemini-2.5-flash-lite

    failure, destruction, or being coated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inverness
    0.56
     Exeter
    0.53
    sa
    0.53
    ui
    0.51
     Edinburgh
    0.50
     Editor
    0.49
    Edinburgh
    0.49
    A
    0.48
     Edin
    0.48
    eda
    0.48
    POSITIVE LOGITS
     degenerative
    0.46
     graisse
    0.44
    ᓯ
    0.43
     réserve
    0.42
    の位置
    0.41
     chemically
    0.41
    ఖ్య
    0.41
    UnifiedTopology
    0.41
    の影響
    0.40
    掑
    0.40
    Activations Density 0.001%

    No Known Activations