© 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. 54002
    Prev
    Next
    INDEX
    Explanations

    accumulated wealth

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

    fills up or slice of

    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
    Country
    0.48
     Worlds
    0.47
    ם
    0.47
    h
    0.47
     Year
    0.44
    hq
    0.43
     (;
    0.43
    york
    0.43
    ｽ
    0.43
    fic
    0.43
    POSITIVE LOGITS
     petróleo
    0.58
     thăm
    0.57
    íj
    0.52
     случае
    0.51
     paciente
    0.50
     sprzedaży
    0.49
     víz
    0.49
     случаев
    0.48
     célula
    0.48
     परिवेश
    0.48
    Activations Density 0.000%

    No Known Activations