© 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. 84900
    Prev
    Next
    INDEX
    Explanations

    airport on, realize what, the Carrier, coconut milk, population was, missing out, offering approximately, beyond that

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

    mission objectives

    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
    Connect
    0.56
    ഗം
    0.51
    銑
    0.46
    タック
    0.45
    setWidth
    0.44
    iles
    0.43
     practic
    0.43
     pressures
    0.43
    𝒟
    0.43
     แรง
    0.42
    POSITIVE LOGITS
    잎
    0.64
    də
    0.53
     unmarried
    0.52
     বয়সে
    0.51
    蚜
    0.49
    dé
    0.49
    ة
    0.49
    χρο
    0.48
    苍
    0.48
     aján
    0.48
    Activations Density 0.001%

    No Known Activations