© 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. 89189
    Prev
    Next
    INDEX
    Explanations

    descriptions of options and features

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

    conscious intent / leave of absence

    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
    隆
    0.47
    る
    0.46
    ۷
    0.46
    栓
    0.45
    િવ
    0.44
    리스
    0.44
    릭
    0.44
    تل
    0.44
    ାର
    0.44
    K
    0.44
    POSITIVE LOGITS
    führt
    0.55
    victoria
    0.48
    fö
    0.47
    vertices
    0.46
    point
    0.46
     querem
    0.46
    ঘ্রই
    0.44
    irano
    0.44
     seeks
    0.43
    erView
    0.43
    Activations Density 0.001%

    No Known Activations