© 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. 132843
    Prev
    Next
    INDEX
    Explanations

    marketing program

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

    major disruption, erosion control, drug discovery

    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
     말이
    0.52
     출연
    0.49
     남아
    0.48
     strife
    0.47
     응
    0.47
     हालात
    0.47
     Ejec
    0.46
     получилось
    0.46
    朊
    0.46
     बनाई
    0.46
    POSITIVE LOGITS
    ZIP
    0.47
    Pierce
    0.45
    。
    0.45
     Pier
    0.43
    的天
    0.43
    uran
    0.42
     Closure
    0.42
    Soup
    0.41
    TextureAsset
    0.41
    =((
    0.41
    Activations Density 0.002%

    No Known Activations