© 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. 156037
    Prev
    Next
    INDEX
    Explanations

    past participles or completed actions

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

    curved paths or distances

    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
     seguimiento
    0.47
    بور
    0.46
    тости
    0.43
     reúne
    0.43
     eleições
    0.43
    🫦
    0.43
    🤏
    0.42
     alimentação
    0.41
     తాజాగా
    0.40
    pocket
    0.40
    POSITIVE LOGITS
     Mankind
    0.50
    綎
    0.48
     Semin
    0.48
     괜
    0.46
     未来
    0.46
     있으며
    0.46
     GED
    0.46
     Refining
    0.45
    ্ব
    0.44
     Mendel
    0.43
    Activations Density 0.000%

    No Known Activations