© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 144349
    Prev
    Next
    INDEX
    Explanations

    lost worlds, signals, temple

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ྩ
    0.43
    在他的
    0.43
    енти
    0.42
    തി
    0.41
     ಎಂಬುದ
    0.41
    spell
    0.40
     পল্ল
    0.39
    娀
    0.39
    形状
    0.39
    生態
    0.39
    POSITIVE LOGITS
    MatContext
    0.54
     अवतार
    0.49
     telah
    0.47
    ätte
    0.46
    ೇನೆ
    0.46
     bude
    0.46
     Gosudarstvennyj
    0.46
     já
    0.46
     toda
    0.46
     lanç
    0.46
    Activations Density 0.000%

    No Known Activations