© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178414
    Prev
    Next
    INDEX
    Explanations

    circle with

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

    following complex instructions

    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
    Negative Logits
    ｼ
    0.53
    朮
    0.45
    chessboard
    0.44
    責
    0.44
    ہیں
    0.43
    ancienne
    0.43
    стары
    0.43
    したので
    0.43
    🔊
    0.43
     underval
    0.42
    POSITIVE LOGITS
     ants
    0.49
    nk
    0.48
     网络
    0.48
    nnnn
    0.47
     banks
    0.46
    nv
    0.46
     lymphatiques
    0.46
     emboss
    0.45
     ।
    0.45
     GLS
    0.45
    Activations Density 0.001%

    No Known Activations