© 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. 113349
    Prev
    Next
    INDEX
    Explanations

    questions and comments

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

    container orchestration security

    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
     vias
    0.52
    وٹی
    0.52
     totam
    0.52
    ulc
    0.51
     capas
    0.50
     henne
    0.49
     layi
    0.48
    )[
    0.48
     informações
    0.47
    oer
    0.47
    POSITIVE LOGITS
    يمه
    0.45
    clientHeight
    0.41
    లు
    0.39
    sburg
    0.39
    сна
    0.39
    的身
    0.39
    .
    0.38
    বহ
    0.38
    ഗത
    0.38
    нал
    0.38
    Activations Density 0.001%

    No Known Activations