© 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. 137223
    Prev
    Next
    INDEX
    Explanations

    mortality, import, requirements, tours, pests, site

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

    phonetic puns and wordplay

    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
    문에
    0.46
    பால
    0.44
    嫉
    0.44
    普及
    0.44
    MACl
    0.43
    誘
    0.43
    𝐛
    0.42
    niem
    0.41
    淋
    0.41
     ਉ
    0.41
    POSITIVE LOGITS
     Mortality
    0.53
    วิต
    0.46
     mortality
    0.46
     Hardy
    0.46
     наконец
    0.45
     Death
    0.44
     NDVI
    0.43
     пришли
    0.43
     acuity
    0.43
    byId
    0.42
    Activations Density 0.000%

    No Known Activations