© 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. 175658
    Prev
    Next
    INDEX
    Explanations

    dumpster leases

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

    predicting masked words

    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
    არი
    0.52
     аны
    0.51
    Liste
    0.50
     этом
    0.50
    ᓂ
    0.50
    嬂
    0.50
    topLeft
    0.50
    坚定
    0.49
    клю
    0.49
    某种
    0.49
    POSITIVE LOGITS
     drink
    0.61
     beer
    0.61
     drinks
    0.60
    ;
    0.58
     booze
    0.58
    -
    0.57
     gallon
    0.56
     drank
    0.55
     water
    0.54
     g
    0.53
    Activations Density 0.000%

    No Known Activations