© 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. 224277
    Prev
    Next
    INDEX
    Explanations

    proprietary, electrodes, person, registry, composition

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

    sew seams

    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
     Floren
    0.50
     alebo
    0.49
     badań
    0.48
     $$\
    0.48
     pracy
    0.47
     Travels
    0.47
     pratis
    0.47
     Tactics
    0.46
     Rapid
    0.46
     Shots
    0.46
    POSITIVE LOGITS
     прямоуго
    0.47
    ༨
    0.47
    梱包
    0.46
    ダイニング
    0.46
    сит
    0.44
    返品
    0.43
    ्ड
    0.43
    их
    0.43
     родители
    0.43
     беремен
    0.42
    Activations Density 0.000%

    No Known Activations