© 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. 123032
    Prev
    Next
    INDEX
    Explanations

    choosing or creating actions

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

    provide me with the text

    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
    :
    0.57
    但不
    0.55
    複雑
    0.54
    dll
    0.52
     :
    0.48
    ：
    0.47
     моего
    0.46
    tun
    0.46
    +:
    0.46
    素敵な
    0.46
    POSITIVE LOGITS
     választ
    0.52
     escolher
    0.50
    CreateWall
    0.50
     వారు
    0.49
    镳
    0.47
     seleccionar
    0.46
     hitter
    0.46
     criar
    0.46
    िवी
    0.44
     commandant
    0.43
    Activations Density 0.001%

    No Known Activations