© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19642
    Prev
    Next
    INDEX
    Explanations

    legal definitions and rulings

    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_31_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
    ľov
    0.46
    時間
    0.46
    寻
    0.45
    而
    0.44
     untersucht
    0.43
     geprüft
    0.42
     информацией
    0.42
    转型
    0.42
     давайте
    0.41
    라마
    0.41
    POSITIVE LOGITS
    is
    0.52
     cubes
    0.52
    n
    0.51
    us
    0.49
    kinds
    0.49
     Z
    0.48
     vara
    0.48
     kinds
    0.47
     resto
    0.47
     subt
    0.47
    Activations Density 0.000%

    No Known Activations