© 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. 123333
    Prev
    Next
    INDEX
    Explanations

    funeral home picnic association

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

    working with clinical equipoise

    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
     ulteriori
    0.53
    ান্তি
    0.50
     vertes
    0.45
     poetry
    0.43
     zostanie
    0.42
    ି
    0.42
     userData
    0.42
     marchio
    0.42
     weitere
    0.41
     uproar
    0.41
    POSITIVE LOGITS
    脚
    0.48
    C
    0.45
    砂糖
    0.45
     පිළ
    0.44
    俸
    0.43
     Tasmania
    0.43
    浦
    0.43
    banks
    0.43
     kitchenette
    0.42
    elihat
    0.42
    Activations Density 0.000%

    No Known Activations