© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 74231
    Prev
    Next
    INDEX
    Explanations

    loved ones, protective function

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

    history is filled with

    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
     a
    0.54
     sucker
    0.53
     introducing
    0.52
     chatting
    0.48
    abang
    0.48
     punch
    0.47
     expanding
    0.46
     increasing
    0.46
     pushing
    0.46
     advancing
    0.46
    POSITIVE LOGITS
    谘
    0.54
     چهار
    0.53
     আত্মসমর্পণ
    0.50
     gacche
    0.50
     şə
    0.49
     достига
    0.48
     Москвы
    0.47
    álni
    0.47
     CONTAINER
    0.47
    lač
    0.47
    Activations Density 0.001%

    No Known Activations