© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9949
    Prev
    Next
    INDEX
    Explanations

    clothing and accommodation

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

    sneakers and boots

    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_40_width_16k_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
    证据
    0.45
    炎症
    0.44
     evi
    0.44
    不稳定
    0.44
     足
    0.43
     einges
    0.41
    钳
    0.41
     CC
    0.39
     evidence
    0.38
     guy
    0.38
    POSITIVE LOGITS
     embroidered
    0.43
     kurta
    0.42
     chinos
    0.42
    Wallet
    0.40
     trainers
    0.40
     blouses
    0.40
     waistcoat
    0.40
     sneakers
    0.39
     sweatshirts
    0.39
    トート
    0.39
    Activations Density 0.032%

    No Known Activations