© 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. 222615
    Prev
    Next
    INDEX
    Explanations

    continue reading

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

    dealing with specifics

    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
     MAIL
    0.57
     Potatoes
    0.52
     Whittier
    0.51
     neer
    0.50
     conte
    0.49
     QUESTION
    0.47
     WOOD
    0.47
    蓟
    0.47
     whirlpool
    0.47
     MATHEMAT
    0.47
    POSITIVE LOGITS
    ensing
    0.52
    iket
    0.52
    jų
    0.52
    cycled
    0.52
    ilä
    0.50
    idos
    0.50
    3
    0.50
    ipal
    0.49
    长
    0.48
    織
    0.48
    Activations Density 0.001%

    No Known Activations