© 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. 142964
    Prev
    Next
    INDEX
    Explanations

    N.p

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

    luxurious accommodations, raw materials, certificates

    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
    ʼn
    0.47
    谶
    0.45
    궪
    0.45
    Theorem
    0.44
    手册
    0.44
    ifikasi
    0.44
    מח
    0.43
    영어
    0.43
    টেও
    0.43
    Ja
    0.42
    POSITIVE LOGITS
     把
    0.51
     floated
    0.51
     đình
    0.45
     بُ
    0.44
     Board
    0.44
     信
    0.44
     curr
    0.44
     declared
    0.43
     Flax
    0.42
     đươ
    0.42
    Activations Density 0.000%

    No Known Activations