© 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. 182321
    Prev
    Next
    INDEX
    Explanations

    container, docker, container

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

    Rewrite, rephrase, shorten

    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
    J
    0.59
    B
    0.56
    T
    0.55
    K
    0.53
    Sof
    0.52
    Head
    0.50
    json
    0.50
    Z
    0.50
    the
    0.50
    ت
    0.50
    POSITIVE LOGITS
     cathode
    0.51
     contenedor
    0.51
     lightness
    0.51
     Docker
    0.48
     यथा
    0.47
    पतवार
    0.47
     container
    0.46
     filosof
    0.46
     docker
    0.45
     Tokugawa
    0.45
    Activations Density 0.001%

    No Known Activations