© 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. 141619
    Prev
    Next
    INDEX
    Explanations

    relationship or definition

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

    containers

    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
     Receiving
    0.51
    ვენ
    0.49
     beras
    0.48
    ramique
    0.48
    ayang
    0.48
     WOMEN
    0.47
     feminino
    0.45
    溺
    0.45
     censoring
    0.45
    ankle
    0.45
    POSITIVE LOGITS
     ።
    0.48
     తొలి
    0.44
     ஆண்டில்
    0.43
    يلا
    0.42
     אר
    0.41
     Laurel
    0.41
    还将
    0.41
     кла
    0.40
     بي
    0.40
     nhật
    0.40
    Activations Density 0.001%

    No Known Activations