© 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. 159179
    Prev
    Next
    INDEX
    Explanations

    flu vaccine, last episode, fourth visit

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

    `/usr/local/bin

    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
     MATERIAL
    0.46
    )
    0.46
     Material
    0.45
     PLANS
    0.44
     Controller
    0.43
     SERVICE
    0.43
     Boolean
    0.43
    Ϳ
    0.43
     exh
    0.43
     presto
    0.42
    POSITIVE LOGITS
    underland
    0.50
    atosis
    0.50
    forgettable
    0.48
    illy
    0.48
    ado
    0.47
    rys
    0.46
    independent
    0.45
    ওনা
    0.45
    independence
    0.45
    ires
    0.45
    Activations Density 0.001%

    No Known Activations