© 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. 52998
    Prev
    Next
    INDEX
    Explanations

    new product listings

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

    building, stacking, nucleus, video generation

    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
    بوع
    0.45
     poignant
    0.44
     طور
    0.44
    监听页面
    0.43
    اقه
    0.43
    ણે
    0.42
    ياته
    0.42
    眸
    0.42
     फोटोशूट
    0.42
     Tết
    0.41
    POSITIVE LOGITS
    X
    0.59
     connectors
    0.54
     stack
    0.53
     cards
    0.51
     machines
    0.51
     stacking
    0.51
     modules
    0.51
    、
    0.50
     stacks
    0.50
     boxes
    0.49
    Activations Density 0.000%

    No Known Activations